| { |
| "metadata": { |
| "total_parameters": 2723017728, |
| "total_size": 10892070912 |
| }, |
| "weight_map": { |
| "embeddings.patch_embed.bias": "model-00001-of-00003.safetensors", |
| "embeddings.patch_embed.weight": "model-00001-of-00003.safetensors", |
| "embeddings.position_embedding.weight": "model-00001-of-00003.safetensors", |
| "embeddings.rms_norm.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.0.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.0.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.0.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.0.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.0.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.0.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.0.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.0.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.0.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.1.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.1.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.1.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.1.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.1.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.1.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.1.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.1.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.1.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.10.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.10.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.10.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.10.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.10.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.10.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.10.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.10.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.10.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.11.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.11.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.11.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.11.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.11.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.11.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.11.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.11.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.11.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.12.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.12.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.12.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.12.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.12.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.12.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.12.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.12.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.12.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.13.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.13.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.13.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.13.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.13.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.13.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.13.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.13.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.13.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.14.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.14.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.14.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.14.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.14.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.14.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.14.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.14.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.14.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.15.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.15.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.15.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.15.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.15.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.15.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.15.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.15.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.15.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.16.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.16.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.16.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.16.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.16.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.16.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.16.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.16.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.16.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.17.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.17.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.17.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.17.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.17.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.17.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.17.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.17.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.17.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.18.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.18.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.18.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.18.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.18.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.18.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.18.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.18.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.18.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.19.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.19.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.19.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.19.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.19.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.19.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.19.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.19.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.19.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.2.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.2.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.2.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.2.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.2.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.2.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.2.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.2.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.2.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.20.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.20.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.20.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.20.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.20.ffn.down_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.20.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.20.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.20.rms_norm1.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.20.rms_norm2.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.21.attention.k_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.21.attention.out_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.21.attention.q_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.21.attention.v_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.21.ffn.down_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.21.ffn.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.21.ffn.up_proj.weight": "model-00002-of-00003.safetensors", |
| "encoder.layers.21.rms_norm1.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.21.rms_norm2.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.22.attention.k_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.22.attention.out_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.22.attention.q_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.22.attention.v_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.22.ffn.down_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.22.ffn.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.22.ffn.up_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.22.rms_norm1.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.22.rms_norm2.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.23.attention.k_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.23.attention.out_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.23.attention.q_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.23.attention.v_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.23.ffn.down_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.23.ffn.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.23.ffn.up_proj.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.23.rms_norm1.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.23.rms_norm2.weight": "model-00003-of-00003.safetensors", |
| "encoder.layers.3.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.3.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.3.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.3.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.3.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.3.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.3.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.3.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.3.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.4.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.4.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.4.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.4.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.4.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.4.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.4.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.4.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.4.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.5.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.5.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.5.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.5.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.5.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.5.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.5.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.5.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.5.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.6.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.6.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.6.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.6.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.6.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.6.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.6.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.6.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.6.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.7.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.7.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.7.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.7.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.7.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.7.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.7.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.7.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.7.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.8.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.8.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.8.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.8.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.8.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.8.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.8.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.8.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.8.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.9.attention.k_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.9.attention.out_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.9.attention.q_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.9.attention.v_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.9.ffn.down_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.9.ffn.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.9.ffn.up_proj.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.9.rms_norm1.weight": "model-00001-of-00003.safetensors", |
| "encoder.layers.9.rms_norm2.weight": "model-00001-of-00003.safetensors", |
| "rms_norm.weight": "model-00003-of-00003.safetensors" |
| } |
| } |
|
|
