| { |
| "metadata": { |
| "total_size": 94444914776 |
| }, |
| "weight_map": { |
| "lm_head.biases": "model-00001-of-00018.safetensors", |
| "lm_head.scales": "model-00001-of-00018.safetensors", |
| "lm_head.weight": "model-00001-of-00018.safetensors", |
| "model.embed_tokens.biases": "model-00001-of-00018.safetensors", |
| "model.embed_tokens.scales": "model-00001-of-00018.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00018.safetensors", |
| "model.hyper_connection_mixer.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.hyper_connection_mixer.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.hyper_connection_mixer.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.switch_mlp.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.switch_mlp.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.switch_mlp.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.switch_mlp.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.0.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.key_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.key_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.key_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.norm_conv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.norm_key.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.norm_query.weight": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.layer_multipliers": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.0.biases": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.0.scales": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.0.weight": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.1.biases": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.1.scales": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.1.weight": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.10.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.10.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.10.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.100.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.100.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.100.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.101.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.101.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.101.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.102.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.102.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.102.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.103.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.103.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.103.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.104.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.104.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.104.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.105.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.105.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.105.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.106.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.106.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.106.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.107.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.107.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.107.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.108.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.108.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.108.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.109.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.109.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.109.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.11.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.11.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.11.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.110.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.110.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.110.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.111.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.111.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.111.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.112.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.112.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.112.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.113.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.113.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.113.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.114.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.114.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.114.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.115.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.115.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.115.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.116.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.116.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.116.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.117.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.117.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.117.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.118.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.118.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.118.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.119.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.119.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.119.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.12.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.12.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.12.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.120.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.120.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.120.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.121.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.121.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.121.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.122.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.122.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.122.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.123.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.123.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.123.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.124.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.124.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.124.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.125.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.125.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.125.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.126.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.126.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.126.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.127.biases": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.127.scales": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.127.weight": "model-00018-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.13.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.13.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.13.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.14.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.14.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.14.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.15.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.15.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.15.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.16.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.16.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.16.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.17.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.17.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.17.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.18.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.18.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.18.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.19.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.19.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.19.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.2.biases": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.2.scales": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.2.weight": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.20.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.20.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.20.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.21.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.21.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.21.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.22.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.22.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.22.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.23.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.23.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.23.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.24.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.24.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.24.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.25.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.25.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.25.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.26.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.26.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.26.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.27.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.27.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.27.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.28.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.28.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.28.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.29.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.29.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.29.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.3.biases": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.3.scales": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.3.weight": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.30.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.30.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.30.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.31.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.31.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.31.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.32.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.32.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.32.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.33.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.33.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.33.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.34.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.34.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.34.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.35.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.35.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.35.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.36.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.36.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.36.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.37.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.37.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.37.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.38.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.38.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.38.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.39.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.39.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.39.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.4.biases": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.4.scales": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.4.weight": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.40.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.40.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.40.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.41.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.41.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.41.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.42.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.42.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.42.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.43.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.43.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.43.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.44.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.44.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.44.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.45.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.45.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.45.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.46.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.46.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.46.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.47.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.47.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.47.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.48.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.48.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.48.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.49.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.49.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.49.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.5.biases": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.5.scales": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.5.weight": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.50.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.50.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.50.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.51.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.51.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.51.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.52.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.52.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.52.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.53.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.53.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.53.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.54.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.54.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.54.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.55.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.55.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.55.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.56.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.56.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.56.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.57.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.57.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.57.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.58.biases": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.58.scales": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.58.weight": "model-00015-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.59.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.59.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.59.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.6.biases": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.6.scales": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.6.weight": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.60.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.60.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.60.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.61.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.61.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.61.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.62.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.62.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.62.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.63.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.63.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.63.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.64.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.64.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.64.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.65.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.65.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.65.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.66.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.66.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.66.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.67.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.67.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.67.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.68.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.68.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.68.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.69.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.69.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.69.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.7.biases": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.7.scales": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.7.weight": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.70.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.70.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.70.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.71.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.71.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.71.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.72.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.72.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.72.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.73.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.73.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.73.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.74.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.74.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.74.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.75.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.75.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.75.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.76.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.76.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.76.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.77.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.77.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.77.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.78.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.78.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.78.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.79.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.79.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.79.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.8.biases": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.8.scales": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.8.weight": "model-00013-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.80.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.80.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.80.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.81.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.81.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.81.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.82.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.82.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.82.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.83.biases": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.83.scales": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.83.weight": "model-00016-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.84.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.84.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.84.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.85.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.85.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.85.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.86.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.86.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.86.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.87.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.87.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.87.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.88.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.88.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.88.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.89.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.89.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.89.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.9.biases": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.9.scales": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.9.weight": "model-00014-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.90.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.90.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.90.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.91.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.91.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.91.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.92.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.92.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.92.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.93.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.93.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.93.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.94.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.94.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.94.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.95.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.95.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.95.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.96.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.96.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.96.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.97.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.97.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.97.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.98.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.98.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.98.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.99.biases": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.99.scales": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_embedding.shards.99.weight": "model-00017-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_heads_offsets": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.ple_embedding.ngram_heads_vocab_sizes": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.value_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.value_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.1.ple.value_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.10.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.10.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.11.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.12.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.12.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.13.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.13.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.14.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.14.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.15.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.16.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.16.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00005-of-00018.safetensors", |
| "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00005-of-00018.safetensors", |
| "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00005-of-00018.safetensors", |
| "model.layers.17.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.17.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.18.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.18.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.19.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.2.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.2.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.20.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.20.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00006-of-00018.safetensors", |
| "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00006-of-00018.safetensors", |
| "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00006-of-00018.safetensors", |
| "model.layers.21.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.21.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.22.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.22.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.23.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.24.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.24.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00007-of-00018.safetensors", |
| "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00007-of-00018.safetensors", |
| "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00007-of-00018.safetensors", |
| "model.layers.25.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.25.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.26.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.26.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.27.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.28.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.28.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00008-of-00018.safetensors", |
| "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00008-of-00018.safetensors", |
| "model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00008-of-00018.safetensors", |
| "model.layers.29.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.29.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.3.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.30.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.30.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.31.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.32.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.32.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00009-of-00018.safetensors", |
| "model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00009-of-00018.safetensors", |
| "model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00009-of-00018.safetensors", |
| "model.layers.33.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.33.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.34.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.34.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.35.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.36.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.36.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00010-of-00018.safetensors", |
| "model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00010-of-00018.safetensors", |
| "model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00010-of-00018.safetensors", |
| "model.layers.37.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.37.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.38.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.38.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.39.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.4.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.4.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.40.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.40.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00011-of-00018.safetensors", |
| "model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00011-of-00018.safetensors", |
| "model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00011-of-00018.safetensors", |
| "model.layers.41.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.41.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.42.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.42.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.43.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.43.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.44.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.44.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00013-of-00018.safetensors", |
| "model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00013-of-00018.safetensors", |
| "model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00013-of-00018.safetensors", |
| "model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00018.safetensors", |
| "model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00018.safetensors", |
| "model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00018.safetensors", |
| "model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00012-of-00018.safetensors", |
| "model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00012-of-00018.safetensors", |
| "model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00012-of-00018.safetensors", |
| "model.layers.45.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.45.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp.switch_mlp.down_proj.biases": "model-00013-of-00018.safetensors", |
| "model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00013-of-00018.safetensors", |
| "model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00013-of-00018.safetensors", |
| "model.layers.46.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00018.safetensors", |
| "model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00018.safetensors", |
| "model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00018.safetensors", |
| "model.layers.46.mlp.switch_mlp.up_proj.biases": "model-00013-of-00018.safetensors", |
| "model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00013-of-00018.safetensors", |
| "model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00013-of-00018.safetensors", |
| "model.layers.46.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.46.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp.switch_mlp.down_proj.biases": "model-00013-of-00018.safetensors", |
| "model.layers.47.mlp.switch_mlp.down_proj.scales": "model-00013-of-00018.safetensors", |
| "model.layers.47.mlp.switch_mlp.down_proj.weight": "model-00013-of-00018.safetensors", |
| "model.layers.47.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00018.safetensors", |
| "model.layers.47.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00018.safetensors", |
| "model.layers.47.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00018.safetensors", |
| "model.layers.47.mlp.switch_mlp.up_proj.biases": "model-00013-of-00018.safetensors", |
| "model.layers.47.mlp.switch_mlp.up_proj.scales": "model-00013-of-00018.safetensors", |
| "model.layers.47.mlp.switch_mlp.up_proj.weight": "model-00013-of-00018.safetensors", |
| "model.layers.47.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.47.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00002-of-00018.safetensors", |
| "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00002-of-00018.safetensors", |
| "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00002-of-00018.safetensors", |
| "model.layers.5.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.5.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.6.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.6.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.7.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.indexer.index_qk_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.indexer.index_qk_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.indexer.index_qk_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.indexer.k_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.indexer.q_layernorm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.8.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.8.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.attn_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.attn_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.attn_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.A_log": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.dt_bias": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_a.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_a.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_b.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_b.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_qkv.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_qkv.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_z.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_z.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.out_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.out_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert.down_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert.down_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert.down_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert.gate_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert.gate_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert.up_proj.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert.up_proj.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert.up_proj.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.shared_expert_gate.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00018.safetensors", |
| "model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00018.safetensors", |
| "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00018.safetensors", |
| "model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00003-of-00018.safetensors", |
| "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00003-of-00018.safetensors", |
| "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00003-of-00018.safetensors", |
| "model.layers.9.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp_hyper_connection.input_mix_weight_down.biases": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp_hyper_connection.input_mix_weight_down.scales": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00018.safetensors", |
| "model.layers.9.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00018.safetensors", |
| "mtp.layers.0.mlp.switch_mlp.gate_proj.weight": "model-mtp-experts-gate.safetensors", |
| "mtp.layers.0.mlp.switch_mlp.gate_proj.scales": "model-mtp-experts-gate.safetensors", |
| "mtp.layers.0.mlp.switch_mlp.gate_proj.biases": "model-mtp-experts-gate.safetensors", |
| "mtp.layers.0.mlp.switch_mlp.up_proj.scales": "model-mtp-experts-up.safetensors", |
| "mtp.layers.0.mlp.switch_mlp.up_proj.weight": "model-mtp-experts-up.safetensors", |
| "mtp.layers.0.mlp.switch_mlp.up_proj.biases": "model-mtp-experts-up.safetensors", |
| "mtp.layers.0.mlp.switch_mlp.down_proj.weight": "model-mtp-experts-down.safetensors", |
| "mtp.layers.0.mlp.switch_mlp.down_proj.scales": "model-mtp-experts-down.safetensors", |
| "mtp.layers.0.mlp.switch_mlp.down_proj.biases": "model-mtp-experts-down.safetensors", |
| "mtp.fc_embedding.weight": "model-mtp-runtime.safetensors", |
| "mtp.fc_hidden.weight": "model-mtp-runtime.safetensors", |
| "mtp.hyper_connection_mixer.hc_norm.weight": "model-mtp-runtime.safetensors", |
| "mtp.hyper_connection_mixer.input_mix_weight_down.weight": "model-mtp-runtime.safetensors", |
| "mtp.hyper_connection_mixer.input_mix_weight_up.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.attn_hyper_connection.block_inject_weight.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.attn_hyper_connection.hc_norm.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.attn_hyper_connection.input_mix_weight_down.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.attn_hyper_connection.input_mix_weight_down.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.attn_hyper_connection.input_mix_weight_down.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.attn_hyper_connection.input_mix_weight_up.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.attn_hyper_connection.input_mix_weight_up.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.attn_hyper_connection.input_mix_weight_up.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.gate.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert.down_proj.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert.down_proj.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert.down_proj.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert.gate_proj.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert.gate_proj.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert.gate_proj.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert.up_proj.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert.up_proj.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert.up_proj.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp.shared_expert_gate.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp_hyper_connection.block_inject_weight.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp_hyper_connection.hc_norm.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.indexer.index_qk_proj.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.indexer.index_qk_proj.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.indexer.index_qk_proj.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.indexer.k_layernorm.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.indexer.q_layernorm.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.k_norm.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.k_proj.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.k_proj.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.k_proj.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.o_proj.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.o_proj.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.o_proj.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.q_norm.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.q_proj.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.q_proj.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.q_proj.biases": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.v_proj.weight": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.v_proj.scales": "model-mtp-runtime.safetensors", |
| "mtp.layers.0.self_attn.v_proj.biases": "model-mtp-runtime.safetensors", |
| "mtp.pre_fc_norm_embedding.weight": "model-mtp-runtime.safetensors", |
| "mtp.pre_fc_norm_hidden.weight": "model-mtp-runtime.safetensors" |
| } |
| } |
|
|
