{ "metadata": { "total_size": 158065310908 }, "weight_map": { "language_model.lm_head.biases": "model-00010-of-00031.safetensors", "language_model.lm_head.scales": "model-00010-of-00031.safetensors", "language_model.lm_head.weight": "model-00010-of-00031.safetensors", "language_model.model.embed_tokens.biases": "model-00010-of-00031.safetensors", "language_model.model.embed_tokens.scales": "model-00010-of-00031.safetensors", "language_model.model.embed_tokens.weight": "model-00010-of-00031.safetensors", "language_model.model.hyper_connection_mixer.hc_norm.weight": "model-00001-of-00031.safetensors", "language_model.model.hyper_connection_mixer.input_mix_weight_down.biases": "model-00001-of-00031.safetensors", "language_model.model.hyper_connection_mixer.input_mix_weight_down.scales": "model-00001-of-00031.safetensors", "language_model.model.hyper_connection_mixer.input_mix_weight_down.weight": "model-00001-of-00031.safetensors", "language_model.model.hyper_connection_mixer.input_mix_weight_up.biases": "model-00001-of-00031.safetensors", "language_model.model.hyper_connection_mixer.input_mix_weight_up.scales": "model-00001-of-00031.safetensors", "language_model.model.hyper_connection_mixer.input_mix_weight_up.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.block_inject_weight.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.block_inject_weight.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.hc_norm.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_up.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_up.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.A_log": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.dt_bias": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_a.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_a.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_b.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_b.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_qkv.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_qkv.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_z.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_z.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.norm.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.out_proj.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.out_proj.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.gate.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert.down_proj.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert.down_proj.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert.gate_proj.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert.gate_proj.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert.up_proj.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert.up_proj.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert_gate.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert_gate.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp.switch_mlp.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.0.mlp.switch_mlp.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.0.mlp.switch_mlp.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.0.mlp.switch_mlp.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.block_inject_weight.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.block_inject_weight.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_up.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_up.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.block_inject_weight.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.block_inject_weight.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.hc_norm.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_up.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_up.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.A_log": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.dt_bias": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_a.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_a.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_b.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_b.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_qkv.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_qkv.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_z.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_z.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.norm.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.out_proj.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.out_proj.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.gate.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert.down_proj.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert.down_proj.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert.gate_proj.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert.gate_proj.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert.up_proj.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert.up_proj.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert_gate.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert_gate.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00011-of-00031.safetensors", "language_model.model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00011-of-00031.safetensors", "language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00011-of-00031.safetensors", "language_model.model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00031.safetensors", "language_model.model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00031.safetensors", "language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "language_model.model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00011-of-00031.safetensors", "language_model.model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00011-of-00031.safetensors", "language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00011-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.block_inject_weight.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.block_inject_weight.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_up.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_up.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.key_proj.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.key_proj.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.key_proj.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.norm_conv.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.norm_key.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.norm_query.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.layer_multipliers": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_0.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_0.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_0.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_1.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_1.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_1.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_10.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_10.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_10.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_100.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_100.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_100.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_101.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_101.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_101.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_102.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_102.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_102.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_103.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_103.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_103.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_104.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_104.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_104.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_105.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_105.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_105.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_106.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_106.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_106.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_107.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_107.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_107.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_108.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_108.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_108.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_109.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_109.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_109.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_11.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_11.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_11.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_110.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_110.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_110.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_111.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_111.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_111.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_112.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_112.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_112.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_113.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_113.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_113.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_114.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_114.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_114.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_115.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_115.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_115.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_116.biases": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_116.scales": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_116.weight": "model-00008-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_117.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_117.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_117.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_118.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_118.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_118.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_119.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_119.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_119.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_12.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_12.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_12.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_120.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_120.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_120.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_121.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_121.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_121.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_122.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_122.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_122.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_123.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_123.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_123.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_124.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_124.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_124.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_125.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_125.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_125.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_126.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_126.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_126.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_127.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_127.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_127.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_13.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_13.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_13.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_14.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_14.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_14.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_15.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_15.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_15.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_16.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_16.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_16.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_17.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_17.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_17.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_18.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_18.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_18.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_19.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_19.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_19.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_2.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_2.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_2.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_20.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_20.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_20.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_21.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_21.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_21.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_22.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_22.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_22.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_23.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_23.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_23.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_24.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_24.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_24.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_25.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_25.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_25.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_26.biases": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_26.scales": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_26.weight": "model-00002-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_27.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_27.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_27.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_28.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_28.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_28.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_29.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_29.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_29.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_3.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_3.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_3.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_30.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_30.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_30.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_31.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_31.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_31.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_32.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_32.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_32.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_33.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_33.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_33.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_34.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_34.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_34.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_35.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_35.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_35.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_36.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_36.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_36.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_37.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_37.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_37.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_38.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_38.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_38.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_39.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_39.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_39.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_4.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_4.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_4.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_40.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_40.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_40.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_41.biases": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_41.scales": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_41.weight": "model-00003-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_42.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_42.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_42.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_43.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_43.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_43.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_44.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_44.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_44.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_45.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_45.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_45.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_46.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_46.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_46.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_47.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_47.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_47.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_48.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_48.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_48.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_49.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_49.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_49.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_5.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_5.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_5.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_50.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_50.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_50.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_51.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_51.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_51.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_52.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_52.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_52.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_53.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_53.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_53.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_54.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_54.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_54.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_55.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_55.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_55.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_56.biases": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_56.scales": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_56.weight": "model-00004-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_57.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_57.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_57.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_58.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_58.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_58.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_59.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_59.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_59.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_6.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_6.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_6.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_60.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_60.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_60.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_61.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_61.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_61.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_62.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_62.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_62.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_63.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_63.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_63.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_64.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_64.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_64.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_65.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_65.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_65.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_66.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_66.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_66.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_67.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_67.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_67.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_68.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_68.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_68.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_69.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_69.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_69.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_7.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_7.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_7.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_70.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_70.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_70.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_71.biases": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_71.scales": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_71.weight": "model-00005-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_72.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_72.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_72.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_73.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_73.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_73.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_74.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_74.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_74.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_75.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_75.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_75.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_76.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_76.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_76.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_77.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_77.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_77.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_78.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_78.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_78.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_79.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_79.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_79.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_8.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_8.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_8.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_80.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_80.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_80.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_81.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_81.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_81.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_82.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_82.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_82.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_83.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_83.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_83.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_84.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_84.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_84.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_85.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_85.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_85.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_86.biases": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_86.scales": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_86.weight": "model-00006-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_87.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_87.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_87.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_88.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_88.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_88.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_89.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_89.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_89.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_9.biases": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_9.scales": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_9.weight": "model-00001-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_90.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_90.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_90.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_91.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_91.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_91.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_92.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_92.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_92.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_93.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_93.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_93.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_94.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_94.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_94.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_95.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_95.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_95.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_96.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_96.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_96.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_97.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_97.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_97.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_98.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_98.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_98.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_99.biases": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_99.scales": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_embedding.shard_99.weight": "model-00007-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_heads_offsets": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.ple_embedding.ngram_heads_vocab_sizes": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.value_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.value_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.1.ple.value_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00015-of-00031.safetensors", "language_model.model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00015-of-00031.safetensors", "language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00015-of-00031.safetensors", "language_model.model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00031.safetensors", "language_model.model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00031.safetensors", "language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "language_model.model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00015-of-00031.safetensors", "language_model.model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00015-of-00031.safetensors", "language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00015-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00015-of-00031.safetensors", "language_model.model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00015-of-00031.safetensors", "language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00015-of-00031.safetensors", "language_model.model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00031.safetensors", "language_model.model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00031.safetensors", "language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "language_model.model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00015-of-00031.safetensors", "language_model.model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00015-of-00031.safetensors", "language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00015-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.indexer.index_qk_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.indexer.index_qk_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.indexer.index_qk_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.indexer.k_layernorm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.indexer.q_layernorm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.k_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.k_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.k_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.o_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.o_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.q_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.q_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.q_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.v_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.v_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.11.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00016-of-00031.safetensors", "language_model.model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00016-of-00031.safetensors", "language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00016-of-00031.safetensors", "language_model.model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00031.safetensors", "language_model.model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00031.safetensors", "language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "language_model.model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00015-of-00031.safetensors", "language_model.model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00015-of-00031.safetensors", "language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00015-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00016-of-00031.safetensors", "language_model.model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00016-of-00031.safetensors", "language_model.model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00016-of-00031.safetensors", "language_model.model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00031.safetensors", "language_model.model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00031.safetensors", "language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "language_model.model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00016-of-00031.safetensors", "language_model.model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00016-of-00031.safetensors", "language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00016-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00016-of-00031.safetensors", "language_model.model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00016-of-00031.safetensors", "language_model.model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00016-of-00031.safetensors", "language_model.model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00031.safetensors", "language_model.model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00031.safetensors", "language_model.model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "language_model.model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00016-of-00031.safetensors", "language_model.model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00016-of-00031.safetensors", "language_model.model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00016-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00017-of-00031.safetensors", "language_model.model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00017-of-00031.safetensors", "language_model.model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00017-of-00031.safetensors", "language_model.model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00031.safetensors", "language_model.model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00031.safetensors", "language_model.model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "language_model.model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00017-of-00031.safetensors", "language_model.model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00017-of-00031.safetensors", "language_model.model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00017-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.indexer.index_qk_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.indexer.index_qk_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.indexer.index_qk_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.indexer.k_layernorm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.indexer.q_layernorm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.k_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.k_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.k_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.o_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.o_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.q_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.q_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.q_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.v_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.v_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.15.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00017-of-00031.safetensors", "language_model.model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00017-of-00031.safetensors", "language_model.model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00017-of-00031.safetensors", "language_model.model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00031.safetensors", "language_model.model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00031.safetensors", "language_model.model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "language_model.model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00017-of-00031.safetensors", "language_model.model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00017-of-00031.safetensors", "language_model.model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00017-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00018-of-00031.safetensors", "language_model.model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00018-of-00031.safetensors", "language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00018-of-00031.safetensors", "language_model.model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00031.safetensors", "language_model.model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00031.safetensors", "language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "language_model.model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00018-of-00031.safetensors", "language_model.model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00018-of-00031.safetensors", "language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00018-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00018-of-00031.safetensors", "language_model.model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00018-of-00031.safetensors", "language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00018-of-00031.safetensors", "language_model.model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00018-of-00031.safetensors", "language_model.model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00031.safetensors", "language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "language_model.model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00018-of-00031.safetensors", "language_model.model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00018-of-00031.safetensors", "language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00018-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00019-of-00031.safetensors", "language_model.model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00019-of-00031.safetensors", "language_model.model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00019-of-00031.safetensors", "language_model.model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00018-of-00031.safetensors", "language_model.model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00031.safetensors", "language_model.model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "language_model.model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00018-of-00031.safetensors", "language_model.model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00018-of-00031.safetensors", "language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00018-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.indexer.index_qk_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.indexer.index_qk_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.indexer.index_qk_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.indexer.k_layernorm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.indexer.q_layernorm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.k_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.k_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.k_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.o_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.o_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.q_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.q_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.q_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.v_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.v_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.19.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00011-of-00031.safetensors", "language_model.model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00011-of-00031.safetensors", "language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00011-of-00031.safetensors", "language_model.model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00031.safetensors", "language_model.model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00031.safetensors", "language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "language_model.model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00011-of-00031.safetensors", "language_model.model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00011-of-00031.safetensors", "language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00011-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00019-of-00031.safetensors", "language_model.model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00019-of-00031.safetensors", "language_model.model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00019-of-00031.safetensors", "language_model.model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00031.safetensors", "language_model.model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00019-of-00031.safetensors", "language_model.model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "language_model.model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00019-of-00031.safetensors", "language_model.model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00019-of-00031.safetensors", "language_model.model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00019-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00019-of-00031.safetensors", "language_model.model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00019-of-00031.safetensors", "language_model.model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00019-of-00031.safetensors", "language_model.model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00031.safetensors", "language_model.model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00019-of-00031.safetensors", "language_model.model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "language_model.model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00019-of-00031.safetensors", "language_model.model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00019-of-00031.safetensors", "language_model.model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00019-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00020-of-00031.safetensors", "language_model.model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00020-of-00031.safetensors", "language_model.model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00020-of-00031.safetensors", "language_model.model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00031.safetensors", "language_model.model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00031.safetensors", "language_model.model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "language_model.model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00020-of-00031.safetensors", "language_model.model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00020-of-00031.safetensors", "language_model.model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00020-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00020-of-00031.safetensors", "language_model.model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00020-of-00031.safetensors", "language_model.model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00020-of-00031.safetensors", "language_model.model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00031.safetensors", "language_model.model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00031.safetensors", "language_model.model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "language_model.model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00020-of-00031.safetensors", "language_model.model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00020-of-00031.safetensors", "language_model.model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00020-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.indexer.index_qk_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.indexer.index_qk_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.indexer.index_qk_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.indexer.k_layernorm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.indexer.q_layernorm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.k_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.k_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.k_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.o_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.o_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.q_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.q_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.q_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.v_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.v_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.23.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00021-of-00031.safetensors", "language_model.model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00021-of-00031.safetensors", "language_model.model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00021-of-00031.safetensors", "language_model.model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00031.safetensors", "language_model.model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00031.safetensors", "language_model.model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "language_model.model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00021-of-00031.safetensors", "language_model.model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00021-of-00031.safetensors", "language_model.model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00021-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_up.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_up.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.A_log": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.conv1d.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.dt_bias": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_a.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_a.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_a.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_b.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_b.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_b.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_qkv.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_qkv.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_z.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_z.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.in_proj_z.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.out_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.out_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.linear_attn.out_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert.down_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert.down_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert.down_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert.gate_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert.gate_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert.up_proj.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert.up_proj.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert.up_proj.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert_gate.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert_gate.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.shared_expert_gate.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00021-of-00031.safetensors", "language_model.model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00021-of-00031.safetensors", "language_model.model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00021-of-00031.safetensors", "language_model.model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00021-of-00031.safetensors", "language_model.model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00031.safetensors", "language_model.model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "language_model.model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00021-of-00031.safetensors", "language_model.model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00021-of-00031.safetensors", "language_model.model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00021-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.block_inject_weight.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.block_inject_weight.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_down.biases": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_down.scales": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00022-of-00031.safetensors", "language_model.model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00022-of-00031.safetensors", "language_model.model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00022-of-00031.safetensors", "language_model.model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00021-of-00031.safetensors", "language_model.model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00031.safetensors", "language_model.model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "language_model.model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00021-of-00031.safetensors", "language_model.model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00021-of-00031.safetensors", "language_model.model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00021-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00022-of-00031.safetensors", "language_model.model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00022-of-00031.safetensors", "language_model.model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00022-of-00031.safetensors", "language_model.model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00031.safetensors", "language_model.model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00022-of-00031.safetensors", "language_model.model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "language_model.model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00022-of-00031.safetensors", "language_model.model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00022-of-00031.safetensors", "language_model.model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00022-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.indexer.index_qk_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.indexer.index_qk_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.indexer.index_qk_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.indexer.k_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.indexer.q_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.k_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.k_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.k_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.o_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.o_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.q_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.q_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.q_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.v_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.v_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.27.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00022-of-00031.safetensors", "language_model.model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00022-of-00031.safetensors", "language_model.model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00022-of-00031.safetensors", "language_model.model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00031.safetensors", "language_model.model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00022-of-00031.safetensors", "language_model.model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "language_model.model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00022-of-00031.safetensors", "language_model.model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00022-of-00031.safetensors", "language_model.model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00022-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00023-of-00031.safetensors", "language_model.model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00023-of-00031.safetensors", "language_model.model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00023-of-00031.safetensors", "language_model.model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00031.safetensors", "language_model.model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00031.safetensors", "language_model.model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "language_model.model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00023-of-00031.safetensors", "language_model.model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00023-of-00031.safetensors", "language_model.model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00023-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00012-of-00031.safetensors", "language_model.model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00012-of-00031.safetensors", "language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00012-of-00031.safetensors", "language_model.model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00031.safetensors", "language_model.model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00031.safetensors", "language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "language_model.model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00012-of-00031.safetensors", "language_model.model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00012-of-00031.safetensors", "language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00012-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.indexer.index_qk_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.indexer.index_qk_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.indexer.index_qk_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.indexer.k_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.indexer.q_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.k_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.k_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.k_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.o_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.o_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.q_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.q_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.q_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.v_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.v_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.3.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00023-of-00031.safetensors", "language_model.model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00023-of-00031.safetensors", "language_model.model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00023-of-00031.safetensors", "language_model.model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00031.safetensors", "language_model.model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00031.safetensors", "language_model.model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "language_model.model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00023-of-00031.safetensors", "language_model.model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00023-of-00031.safetensors", "language_model.model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00023-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00024-of-00031.safetensors", "language_model.model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00024-of-00031.safetensors", "language_model.model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00024-of-00031.safetensors", "language_model.model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00031.safetensors", "language_model.model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00031.safetensors", "language_model.model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "language_model.model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00024-of-00031.safetensors", "language_model.model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00024-of-00031.safetensors", "language_model.model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00024-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.indexer.index_qk_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.indexer.index_qk_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.indexer.index_qk_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.indexer.k_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.indexer.q_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.k_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.k_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.k_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.o_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.o_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.q_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.q_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.q_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.v_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.v_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.31.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00024-of-00031.safetensors", "language_model.model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00024-of-00031.safetensors", "language_model.model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00024-of-00031.safetensors", "language_model.model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00024-of-00031.safetensors", "language_model.model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00024-of-00031.safetensors", "language_model.model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "language_model.model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00024-of-00031.safetensors", "language_model.model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00024-of-00031.safetensors", "language_model.model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00024-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00025-of-00031.safetensors", "language_model.model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00025-of-00031.safetensors", "language_model.model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00025-of-00031.safetensors", "language_model.model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00024-of-00031.safetensors", "language_model.model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00024-of-00031.safetensors", "language_model.model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "language_model.model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00024-of-00031.safetensors", "language_model.model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00024-of-00031.safetensors", "language_model.model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00024-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00025-of-00031.safetensors", "language_model.model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00025-of-00031.safetensors", "language_model.model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00025-of-00031.safetensors", "language_model.model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00025-of-00031.safetensors", "language_model.model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00025-of-00031.safetensors", "language_model.model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "language_model.model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00025-of-00031.safetensors", "language_model.model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00025-of-00031.safetensors", "language_model.model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00025-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00025-of-00031.safetensors", "language_model.model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00025-of-00031.safetensors", "language_model.model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00025-of-00031.safetensors", "language_model.model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00025-of-00031.safetensors", "language_model.model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00025-of-00031.safetensors", "language_model.model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "language_model.model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00025-of-00031.safetensors", "language_model.model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00025-of-00031.safetensors", "language_model.model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00025-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.indexer.index_qk_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.indexer.index_qk_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.indexer.index_qk_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.indexer.k_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.indexer.q_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.k_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.k_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.k_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.o_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.o_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.q_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.q_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.q_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.v_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.v_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.35.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00026-of-00031.safetensors", "language_model.model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00026-of-00031.safetensors", "language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00026-of-00031.safetensors", "language_model.model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00031.safetensors", "language_model.model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00031.safetensors", "language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "language_model.model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00026-of-00031.safetensors", "language_model.model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00026-of-00031.safetensors", "language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00026-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00026-of-00031.safetensors", "language_model.model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00026-of-00031.safetensors", "language_model.model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00026-of-00031.safetensors", "language_model.model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00031.safetensors", "language_model.model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00031.safetensors", "language_model.model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "language_model.model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00026-of-00031.safetensors", "language_model.model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00026-of-00031.safetensors", "language_model.model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00026-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00027-of-00031.safetensors", "language_model.model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00027-of-00031.safetensors", "language_model.model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00027-of-00031.safetensors", "language_model.model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00031.safetensors", "language_model.model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00031.safetensors", "language_model.model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "language_model.model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00027-of-00031.safetensors", "language_model.model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00027-of-00031.safetensors", "language_model.model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00027-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00027-of-00031.safetensors", "language_model.model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00027-of-00031.safetensors", "language_model.model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00027-of-00031.safetensors", "language_model.model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00027-of-00031.safetensors", "language_model.model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00027-of-00031.safetensors", "language_model.model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "language_model.model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00027-of-00031.safetensors", "language_model.model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00027-of-00031.safetensors", "language_model.model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00027-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.indexer.index_qk_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.indexer.index_qk_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.indexer.index_qk_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.indexer.k_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.indexer.q_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.k_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.k_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.k_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.o_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.o_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.q_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.q_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.q_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.v_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.v_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.39.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00012-of-00031.safetensors", "language_model.model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00012-of-00031.safetensors", "language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00012-of-00031.safetensors", "language_model.model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00031.safetensors", "language_model.model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00031.safetensors", "language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "language_model.model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00012-of-00031.safetensors", "language_model.model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00012-of-00031.safetensors", "language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00012-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00028-of-00031.safetensors", "language_model.model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00028-of-00031.safetensors", "language_model.model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00028-of-00031.safetensors", "language_model.model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00027-of-00031.safetensors", "language_model.model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00027-of-00031.safetensors", "language_model.model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "language_model.model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00027-of-00031.safetensors", "language_model.model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00027-of-00031.safetensors", "language_model.model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00027-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00028-of-00031.safetensors", "language_model.model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00028-of-00031.safetensors", "language_model.model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00028-of-00031.safetensors", "language_model.model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00028-of-00031.safetensors", "language_model.model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00028-of-00031.safetensors", "language_model.model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "language_model.model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00028-of-00031.safetensors", "language_model.model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00028-of-00031.safetensors", "language_model.model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00028-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00028-of-00031.safetensors", "language_model.model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00028-of-00031.safetensors", "language_model.model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00028-of-00031.safetensors", "language_model.model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00028-of-00031.safetensors", "language_model.model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00028-of-00031.safetensors", "language_model.model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "language_model.model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00028-of-00031.safetensors", "language_model.model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00028-of-00031.safetensors", "language_model.model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00028-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00029-of-00031.safetensors", "language_model.model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00029-of-00031.safetensors", "language_model.model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00029-of-00031.safetensors", "language_model.model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00031.safetensors", "language_model.model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00031.safetensors", "language_model.model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "language_model.model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00029-of-00031.safetensors", "language_model.model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00029-of-00031.safetensors", "language_model.model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00029-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.indexer.index_qk_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.indexer.index_qk_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.indexer.index_qk_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.indexer.k_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.indexer.q_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.k_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.k_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.k_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.o_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.o_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.q_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.q_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.q_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.v_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.v_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.43.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00029-of-00031.safetensors", "language_model.model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00029-of-00031.safetensors", "language_model.model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00029-of-00031.safetensors", "language_model.model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00031.safetensors", "language_model.model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00031.safetensors", "language_model.model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "language_model.model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00029-of-00031.safetensors", "language_model.model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00029-of-00031.safetensors", "language_model.model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00029-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00030-of-00031.safetensors", "language_model.model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00030-of-00031.safetensors", "language_model.model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00030-of-00031.safetensors", "language_model.model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00031.safetensors", "language_model.model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00031.safetensors", "language_model.model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "language_model.model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00030-of-00031.safetensors", "language_model.model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00030-of-00031.safetensors", "language_model.model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00030-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp.switch_mlp.down_proj.biases": "model-00030-of-00031.safetensors", "language_model.model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00030-of-00031.safetensors", "language_model.model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00030-of-00031.safetensors", "language_model.model.layers.46.mlp.switch_mlp.gate_proj.biases": "model-00030-of-00031.safetensors", "language_model.model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00030-of-00031.safetensors", "language_model.model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "language_model.model.layers.46.mlp.switch_mlp.up_proj.biases": "model-00030-of-00031.safetensors", "language_model.model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00030-of-00031.safetensors", "language_model.model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00030-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp.switch_mlp.down_proj.biases": "model-00031-of-00031.safetensors", "language_model.model.layers.47.mlp.switch_mlp.down_proj.scales": "model-00031-of-00031.safetensors", "language_model.model.layers.47.mlp.switch_mlp.down_proj.weight": "model-00031-of-00031.safetensors", "language_model.model.layers.47.mlp.switch_mlp.gate_proj.biases": "model-00030-of-00031.safetensors", "language_model.model.layers.47.mlp.switch_mlp.gate_proj.scales": "model-00030-of-00031.safetensors", "language_model.model.layers.47.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "language_model.model.layers.47.mlp.switch_mlp.up_proj.biases": "model-00030-of-00031.safetensors", "language_model.model.layers.47.mlp.switch_mlp.up_proj.scales": "model-00030-of-00031.safetensors", "language_model.model.layers.47.mlp.switch_mlp.up_proj.weight": "model-00030-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.indexer.index_qk_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.indexer.index_qk_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.indexer.index_qk_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.indexer.k_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.indexer.q_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.k_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.k_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.k_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.o_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.o_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.q_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.q_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.q_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.v_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.v_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.47.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00013-of-00031.safetensors", "language_model.model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00013-of-00031.safetensors", "language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00013-of-00031.safetensors", "language_model.model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00031.safetensors", "language_model.model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00031.safetensors", "language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "language_model.model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00012-of-00031.safetensors", "language_model.model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00012-of-00031.safetensors", "language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00012-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00013-of-00031.safetensors", "language_model.model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00013-of-00031.safetensors", "language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00013-of-00031.safetensors", "language_model.model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00031.safetensors", "language_model.model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00031.safetensors", "language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "language_model.model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00013-of-00031.safetensors", "language_model.model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00013-of-00031.safetensors", "language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00013-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00013-of-00031.safetensors", "language_model.model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00013-of-00031.safetensors", "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00013-of-00031.safetensors", "language_model.model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00031.safetensors", "language_model.model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00031.safetensors", "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "language_model.model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00013-of-00031.safetensors", "language_model.model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00013-of-00031.safetensors", "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00013-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.indexer.index_qk_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.indexer.index_qk_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.indexer.index_qk_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.indexer.k_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.indexer.q_layernorm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.k_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.k_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.k_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.o_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.o_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.q_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.q_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.q_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.v_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.v_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.7.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00014-of-00031.safetensors", "language_model.model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00014-of-00031.safetensors", "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00014-of-00031.safetensors", "language_model.model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00031.safetensors", "language_model.model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00031.safetensors", "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "language_model.model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00014-of-00031.safetensors", "language_model.model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00014-of-00031.safetensors", "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00014-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.A_log": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.conv1d.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.dt_bias": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_a.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_a.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_a.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_b.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_b.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_b.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_qkv.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_qkv.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_z.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_z.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.in_proj_z.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.out_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.out_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.linear_attn.out_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert.down_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert.down_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert.down_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert.gate_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert.gate_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert.up_proj.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert.up_proj.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert.up_proj.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert_gate.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert_gate.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.shared_expert_gate.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00014-of-00031.safetensors", "language_model.model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00014-of-00031.safetensors", "language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00014-of-00031.safetensors", "language_model.model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00031.safetensors", "language_model.model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00031.safetensors", "language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "language_model.model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00014-of-00031.safetensors", "language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00014-of-00031.safetensors", "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00014-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.block_inject_weight.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.block_inject_weight.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010-of-00031.safetensors", "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00031.safetensors", "language_model.mtp.fc_embedding.biases": "model-00031-of-00031.safetensors", "language_model.mtp.fc_embedding.scales": "model-00031-of-00031.safetensors", "language_model.mtp.fc_embedding.weight": "model-00031-of-00031.safetensors", "language_model.mtp.fc_hidden.biases": "model-00031-of-00031.safetensors", "language_model.mtp.fc_hidden.scales": "model-00031-of-00031.safetensors", "language_model.mtp.fc_hidden.weight": "model-00031-of-00031.safetensors", "language_model.mtp.hyper_connection_mixer.hc_norm.weight": "model-00031-of-00031.safetensors", "language_model.mtp.hyper_connection_mixer.input_mix_weight_down.biases": "model-00031-of-00031.safetensors", "language_model.mtp.hyper_connection_mixer.input_mix_weight_down.scales": "model-00031-of-00031.safetensors", "language_model.mtp.hyper_connection_mixer.input_mix_weight_down.weight": "model-00031-of-00031.safetensors", "language_model.mtp.hyper_connection_mixer.input_mix_weight_up.biases": "model-00031-of-00031.safetensors", "language_model.mtp.hyper_connection_mixer.input_mix_weight_up.scales": "model-00031-of-00031.safetensors", "language_model.mtp.hyper_connection_mixer.input_mix_weight_up.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.block_inject_weight.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.block_inject_weight.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.block_inject_weight.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.hc_norm.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_down.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_down.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_down.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_up.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_up.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_up.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.gate.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert.down_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert.down_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert.down_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert.gate_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert.gate_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert.gate_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert.up_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert.up_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert.up_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert_gate.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert_gate.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.shared_expert_gate.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.switch_mlp.down_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.switch_mlp.down_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.switch_mlp.down_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.switch_mlp.up_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.switch_mlp.up_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp.switch_mlp.up_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.block_inject_weight.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.block_inject_weight.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.block_inject_weight.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.hc_norm.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.indexer.index_qk_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.indexer.index_qk_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.indexer.index_qk_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.indexer.k_layernorm.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.indexer.q_layernorm.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.k_norm.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.k_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.k_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.k_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.o_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.o_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.o_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.q_norm.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.q_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.q_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.q_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.v_proj.biases": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.v_proj.scales": "model-00031-of-00031.safetensors", "language_model.mtp.layers.0.self_attn.v_proj.weight": "model-00031-of-00031.safetensors", "language_model.mtp.pre_fc_norm_embedding.weight": "model-00031-of-00031.safetensors", "language_model.mtp.pre_fc_norm_hidden.weight": "model-00031-of-00031.safetensors", "vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.0.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.1.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.10.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.11.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.12.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.13.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.14.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.15.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.16.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.17.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.18.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.19.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.2.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.20.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.21.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.22.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.23.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.24.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.25.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.26.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.3.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.4.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.5.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.6.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.7.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.8.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.norm1.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.norm1.weight": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.norm2.bias": "model-00001-of-00031.safetensors", "vision_tower.blocks.9.norm2.weight": "model-00001-of-00031.safetensors", "vision_tower.merger.linear_fc1.bias": "model-00001-of-00031.safetensors", "vision_tower.merger.linear_fc1.weight": "model-00001-of-00031.safetensors", "vision_tower.merger.linear_fc2.bias": "model-00001-of-00031.safetensors", "vision_tower.merger.linear_fc2.weight": "model-00001-of-00031.safetensors", "vision_tower.merger.norm.bias": "model-00001-of-00031.safetensors", "vision_tower.merger.norm.weight": "model-00001-of-00031.safetensors", "vision_tower.patch_embed.proj.bias": "model-00001-of-00031.safetensors", "vision_tower.patch_embed.proj.weight": "model-00001-of-00031.safetensors", "vision_tower.pos_embed.weight": "model-00001-of-00031.safetensors" } }