| { |
| "metadata": { |
| "total_size": 5511307520, |
| "total_parameters": 8467856128 |
| }, |
| "weight_map": { |
| "model.embed_tokens.biases": "model-00001-of-00002.safetensors", |
| "model.embed_tokens.scales": "model-00001-of-00002.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00002.safetensors", |
| "model.embedding_norm.weight": "model-00002-of-00002.safetensors", |
| "model.layers.0.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.0.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.0.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.0.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.0.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.feed_forward.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.0.feed_forward.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.feed_forward.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.0.feed_forward.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.feed_forward.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.0.feed_forward.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.1.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.1.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.1.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.1.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.feed_forward.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.1.feed_forward.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.feed_forward.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.1.feed_forward.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.feed_forward.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.1.feed_forward.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.10.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.11.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.11.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.11.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.11.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.11.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.12.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.12.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.12.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.12.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.12.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.13.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.13.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.13.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.13.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.13.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.14.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.15.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.15.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.15.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.15.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.15.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.16.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.16.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.16.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.16.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.16.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.17.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.17.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.17.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.17.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.17.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.18.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.19.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.19.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.19.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.19.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.19.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.2.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.20.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.20.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.20.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.20.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.20.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.21.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.22.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.22.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.22.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.22.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.22.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.23.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.23.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.23.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.23.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.23.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.23.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.23.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.23.feed_forward.expert_bias": "model-00002-of-00002.safetensors", |
| "model.layers.23.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.23.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.23.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.23.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors", |
| "model.layers.23.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors", |
| "model.layers.23.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.23.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.23.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.23.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.23.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors", |
| "model.layers.23.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors", |
| "model.layers.23.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors", |
| "model.layers.23.operator_norm.weight": "model-00002-of-00002.safetensors", |
| "model.layers.3.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.3.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.3.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.3.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.3.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.3.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.3.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.3.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.3.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.4.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.4.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.4.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.4.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.4.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.4.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.4.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.4.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.4.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.5.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.5.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.5.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.5.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.5.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.5.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.5.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.5.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.5.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.6.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.7.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.7.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.7.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.7.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.7.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.7.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.7.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.7.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.7.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.8.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.8.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.8.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.8.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.8.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.8.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.8.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.8.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.8.operator_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.9.conv.conv.weight": "model-00001-of-00002.safetensors", |
| "model.layers.9.conv.in_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.9.conv.in_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.9.conv.in_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.9.conv.out_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.9.conv.out_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.9.conv.out_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.expert_bias": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.gate.biases": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.gate.scales": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.gate.weight": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors", |
| "model.layers.9.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.9.operator_norm.weight": "model-00001-of-00002.safetensors" |
| } |
| } |
