| { | |
| "metadata": { | |
| "total_size": 11805587200 | |
| }, | |
| "weight_map": { | |
| "embeddings.class_embedding": "pytorch_model-00001-of-00002.bin", | |
| "embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin", | |
| "embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin", | |
| "embeddings.position_embedding": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.0.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.1.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.10.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.11.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.12.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.13.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.14.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.15.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.16.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.17.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.18.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.19.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.2.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.20.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.21.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.22.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.23.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.24.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.25.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.26.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.27.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.28.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.29.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.3.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.30.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.31.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.32.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.33.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.34.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.35.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.36.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.37.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.38.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.39.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.4.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.40.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.40.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.40.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.40.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.40.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.40.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.40.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.40.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.40.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.40.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.40.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.40.norm1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.40.norm2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.attn.k_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.attn.proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.attn.proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.attn.q_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.attn.qkv.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.ls1": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.ls2": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.norm1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.41.norm2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.attn.k_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.attn.proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.attn.proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.attn.q_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.attn.qkv.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.ls1": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.ls2": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.norm1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.42.norm2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.attn.k_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.attn.proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.attn.proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.attn.q_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.attn.qkv.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.ls1": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.ls2": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.norm1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.43.norm2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.attn.k_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.attn.proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.attn.proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.attn.q_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.attn.qkv.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.ls1": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.ls2": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.norm1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.44.norm2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.attn.k_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.attn.proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.attn.proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.attn.q_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.attn.qkv.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.ls1": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.ls2": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.norm1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.45.norm2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.attn.k_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.attn.proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.attn.proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.attn.q_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.attn.qkv.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.ls1": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.ls2": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.norm1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.46.norm2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.attn.k_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.attn.proj.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.attn.proj.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.attn.q_norm.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.attn.qkv.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.ls1": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.ls2": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.norm1.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.47.norm2.weight": "pytorch_model-00002-of-00002.bin", | |
| "encoder.layers.5.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.5.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.6.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.7.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.8.norm2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.attn.k_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.attn.proj.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.attn.proj.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.attn.q_norm.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.attn.qkv.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.ls1": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.ls2": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.norm1.weight": "pytorch_model-00001-of-00002.bin", | |
| "encoder.layers.9.norm2.weight": "pytorch_model-00001-of-00002.bin" | |
| } | |
| } | |