model.safetensors.index.json

{
  "metadata": {
    "total_parameters": 1904650240,
    "total_size": 7618600960
  },
  "weight_map": {
    "encoder.embeddings.img_mod_embed": "model-00001-of-00004.safetensors",
    "encoder.embeddings.patch_embeddings.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.embeddings.patch_embeddings.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.embeddings.patch_embeddings_img.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.embeddings.patch_embeddings_img.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.embeddings.video_mod_embed": "model-00001-of-00004.safetensors",
    "encoder.layer.0.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.0.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.0.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.0.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.0.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.0.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.0.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.0.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.0.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.0.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.0.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.0.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.1.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.1.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.1.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.1.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.1.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.1.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.1.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.1.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.1.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.1.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.1.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.1.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.10.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.10.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.10.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.10.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.10.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.10.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.10.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.10.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.10.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.10.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.10.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.10.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.11.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.11.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.11.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.11.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.11.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.11.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.11.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.11.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.11.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.11.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.11.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.11.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.12.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.12.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.12.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.12.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.12.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.12.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.12.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.12.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.12.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.12.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.12.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.12.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.12.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.12.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.13.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.13.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.13.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.13.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.13.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.13.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.13.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.13.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.13.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.13.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.13.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.13.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.13.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.13.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.13.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.13.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.14.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.14.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.14.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.14.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.14.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.14.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.14.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.14.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.14.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.14.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.14.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.14.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.14.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.14.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.14.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.14.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.15.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.15.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.15.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.15.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.15.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.15.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.15.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.15.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.15.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.15.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.15.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.15.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.15.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.15.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.15.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.15.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.16.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.16.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.16.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.16.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.16.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.16.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.16.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.16.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.16.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.16.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.16.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.16.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.16.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.16.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.16.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.16.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.17.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.17.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.17.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.17.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.17.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.17.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.17.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.17.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.17.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.17.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.17.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.17.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.17.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.17.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.17.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.17.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.18.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.18.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.18.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.18.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.18.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.18.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.18.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.18.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.18.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.18.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.18.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.18.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.18.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.18.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.18.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.18.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.19.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.19.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.19.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.19.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.19.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.19.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.19.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.19.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.19.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.19.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.19.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.19.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.19.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.19.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.19.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.19.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.2.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.2.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.2.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.2.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.2.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.2.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.2.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.2.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.2.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.2.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.2.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.2.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.20.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.20.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.20.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.20.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.20.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.20.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.20.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.20.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.20.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.20.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.20.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.20.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.20.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.20.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.20.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.20.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.21.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.21.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.21.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.21.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.21.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.21.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.21.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.21.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.21.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.21.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.21.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.21.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.21.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.21.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.21.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.21.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.22.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.22.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.22.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.22.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.22.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.22.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.22.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.22.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.22.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.22.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.22.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.22.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.22.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.22.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.22.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.22.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.23.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.23.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.23.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.23.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.23.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.23.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.23.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.23.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.23.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.23.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.23.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.23.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.23.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.23.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.23.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.23.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.24.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.24.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.24.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.24.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.24.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.24.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.24.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.24.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.24.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.24.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.24.mlp.fc2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.24.mlp.fc2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.24.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.24.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.24.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.24.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.25.attention.key.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.25.attention.key.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.25.attention.proj.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.25.attention.proj.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.25.attention.query.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.25.attention.query.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.25.attention.value.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.25.attention.value.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.25.mlp.fc1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.25.mlp.fc1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.25.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.25.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.25.norm1.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.25.norm1.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.25.norm2.bias": "model-00002-of-00004.safetensors",
    "encoder.layer.25.norm2.weight": "model-00002-of-00004.safetensors",
    "encoder.layer.26.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.26.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.26.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.26.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.26.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.26.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.26.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.26.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.26.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.26.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.26.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.26.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.26.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.26.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.26.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.26.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.27.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.27.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.27.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.27.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.27.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.27.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.27.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.27.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.27.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.27.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.27.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.27.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.27.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.27.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.27.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.27.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.28.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.28.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.28.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.28.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.28.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.28.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.28.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.28.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.28.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.28.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.28.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.28.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.28.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.28.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.28.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.28.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.29.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.29.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.29.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.29.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.29.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.29.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.29.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.29.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.29.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.29.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.29.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.29.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.29.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.29.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.29.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.29.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.3.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.3.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.3.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.3.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.3.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.3.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.3.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.3.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.3.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.3.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.3.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.3.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.30.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.30.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.30.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.30.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.30.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.30.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.30.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.30.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.30.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.30.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.30.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.30.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.30.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.30.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.30.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.30.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.31.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.31.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.31.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.31.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.31.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.31.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.31.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.31.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.31.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.31.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.31.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.31.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.31.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.31.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.31.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.31.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.32.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.32.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.32.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.32.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.32.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.32.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.32.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.32.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.32.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.32.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.32.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.32.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.32.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.32.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.32.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.32.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.33.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.33.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.33.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.33.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.33.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.33.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.33.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.33.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.33.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.33.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.33.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.33.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.33.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.33.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.33.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.33.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.34.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.34.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.34.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.34.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.34.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.34.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.34.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.34.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.34.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.34.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.34.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.34.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.34.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.34.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.34.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.34.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.35.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.35.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.35.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.35.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.35.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.35.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.35.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.35.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.35.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.35.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.35.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.35.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.35.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.35.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.35.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.35.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.36.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.36.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.36.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.36.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.36.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.36.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.36.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.36.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.36.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.36.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.36.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.36.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.36.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.36.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.36.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.36.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.37.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.37.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.37.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.37.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.37.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.37.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.37.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.37.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.37.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.37.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.37.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.37.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.37.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.37.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.37.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.37.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.38.attention.key.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.38.attention.key.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.38.attention.proj.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.38.attention.proj.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.38.attention.query.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.38.attention.query.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.38.attention.value.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.38.attention.value.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.38.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.38.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.38.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.38.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.38.norm1.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.38.norm1.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.38.norm2.bias": "model-00003-of-00004.safetensors",
    "encoder.layer.38.norm2.weight": "model-00003-of-00004.safetensors",
    "encoder.layer.39.attention.key.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.39.attention.key.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.39.attention.proj.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.39.attention.proj.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.39.attention.query.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.39.attention.query.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.39.attention.value.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.39.attention.value.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.39.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.39.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.39.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.39.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.39.norm1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.39.norm1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.39.norm2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.39.norm2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.4.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.4.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.4.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.4.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.4.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.4.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.4.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.4.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.4.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.4.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.4.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.4.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.40.attention.key.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.40.attention.key.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.40.attention.proj.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.40.attention.proj.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.40.attention.query.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.40.attention.query.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.40.attention.value.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.40.attention.value.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.40.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.40.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.40.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.40.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.40.norm1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.40.norm1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.40.norm2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.40.norm2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.41.attention.key.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.41.attention.key.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.41.attention.proj.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.41.attention.proj.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.41.attention.query.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.41.attention.query.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.41.attention.value.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.41.attention.value.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.41.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.41.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.41.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.41.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.41.norm1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.41.norm1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.41.norm2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.41.norm2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.42.attention.key.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.42.attention.key.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.42.attention.proj.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.42.attention.proj.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.42.attention.query.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.42.attention.query.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.42.attention.value.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.42.attention.value.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.42.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.42.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.42.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.42.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.42.norm1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.42.norm1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.42.norm2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.42.norm2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.43.attention.key.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.43.attention.key.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.43.attention.proj.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.43.attention.proj.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.43.attention.query.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.43.attention.query.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.43.attention.value.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.43.attention.value.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.43.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.43.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.43.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.43.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.43.norm1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.43.norm1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.43.norm2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.43.norm2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.44.attention.key.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.44.attention.key.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.44.attention.proj.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.44.attention.proj.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.44.attention.query.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.44.attention.query.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.44.attention.value.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.44.attention.value.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.44.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.44.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.44.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.44.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.44.norm1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.44.norm1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.44.norm2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.44.norm2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.45.attention.key.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.45.attention.key.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.45.attention.proj.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.45.attention.proj.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.45.attention.query.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.45.attention.query.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.45.attention.value.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.45.attention.value.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.45.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.45.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.45.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.45.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.45.norm1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.45.norm1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.45.norm2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.45.norm2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.46.attention.key.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.46.attention.key.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.46.attention.proj.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.46.attention.proj.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.46.attention.query.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.46.attention.query.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.46.attention.value.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.46.attention.value.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.46.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.46.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.46.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.46.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.46.norm1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.46.norm1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.46.norm2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.46.norm2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.47.attention.key.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.47.attention.key.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.47.attention.proj.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.47.attention.proj.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.47.attention.query.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.47.attention.query.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.47.attention.value.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.47.attention.value.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.47.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.47.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.47.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.47.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.47.norm1.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.47.norm1.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.47.norm2.bias": "model-00004-of-00004.safetensors",
    "encoder.layer.47.norm2.weight": "model-00004-of-00004.safetensors",
    "encoder.layer.5.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.5.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.5.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.5.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.5.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.5.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.5.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.5.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.5.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.5.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.5.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.5.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.6.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.6.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.6.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.6.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.6.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.6.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.6.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.6.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.6.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.6.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.6.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.6.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.7.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.7.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.7.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.7.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.7.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.7.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.7.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.7.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.7.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.7.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.7.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.7.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.8.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.8.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.8.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.8.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.8.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.8.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.8.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.8.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.8.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.8.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.8.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.8.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.9.attention.key.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.9.attention.key.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.9.attention.proj.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.9.attention.proj.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.9.attention.query.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.9.attention.query.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.9.attention.value.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.9.attention.value.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.9.norm1.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.9.norm1.weight": "model-00001-of-00004.safetensors",
    "encoder.layer.9.norm2.bias": "model-00001-of-00004.safetensors",
    "encoder.layer.9.norm2.weight": "model-00001-of-00004.safetensors",
    "encoder.norms_block.0.bias": "model-00004-of-00004.safetensors",
    "encoder.norms_block.0.weight": "model-00004-of-00004.safetensors",
    "encoder.norms_block.1.bias": "model-00004-of-00004.safetensors",
    "encoder.norms_block.1.weight": "model-00004-of-00004.safetensors",
    "encoder.norms_block.2.bias": "model-00004-of-00004.safetensors",
    "encoder.norms_block.2.weight": "model-00004-of-00004.safetensors",
    "encoder.norms_block.3.bias": "model-00004-of-00004.safetensors",
    "encoder.norms_block.3.weight": "model-00004-of-00004.safetensors",
    "predictor.embeddings.img_mod_embed": "model-00004-of-00004.safetensors",
    "predictor.embeddings.mask_tokens.0": "model-00004-of-00004.safetensors",
    "predictor.embeddings.mask_tokens.1": "model-00004-of-00004.safetensors",
    "predictor.embeddings.mask_tokens.2": "model-00004-of-00004.safetensors",
    "predictor.embeddings.mask_tokens.3": "model-00004-of-00004.safetensors",
    "predictor.embeddings.mask_tokens.4": "model-00004-of-00004.safetensors",
    "predictor.embeddings.mask_tokens.5": "model-00004-of-00004.safetensors",
    "predictor.embeddings.mask_tokens.6": "model-00004-of-00004.safetensors",
    "predictor.embeddings.mask_tokens.7": "model-00004-of-00004.safetensors",
    "predictor.embeddings.predictor_embed.0.bias": "model-00004-of-00004.safetensors",
    "predictor.embeddings.predictor_embed.0.weight": "model-00004-of-00004.safetensors",
    "predictor.embeddings.predictor_embed.2.bias": "model-00004-of-00004.safetensors",
    "predictor.embeddings.predictor_embed.2.weight": "model-00004-of-00004.safetensors",
    "predictor.embeddings.video_mod_embed": "model-00004-of-00004.safetensors",
    "predictor.layer.0.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.0.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.0.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.0.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.0.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.0.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.0.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.0.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.0.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.0.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.0.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.0.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.1.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.1.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.1.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.1.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.1.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.1.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.1.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.1.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.1.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.1.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.1.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.1.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.10.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.10.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.10.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.10.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.10.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.10.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.10.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.10.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.10.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.10.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.10.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.10.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.11.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.11.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.11.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.11.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.11.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.11.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.11.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.11.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.11.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.11.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.11.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.11.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.12.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.12.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.12.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.12.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.12.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.12.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.12.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.12.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.12.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.12.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.12.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.12.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.13.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.13.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.13.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.13.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.13.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.13.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.13.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.13.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.13.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.13.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.13.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.13.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.14.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.14.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.14.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.14.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.14.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.14.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.14.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.14.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.14.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.14.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.14.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.14.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.15.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.15.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.15.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.15.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.15.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.15.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.15.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.15.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.15.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.15.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.15.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.15.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.16.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.16.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.16.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.16.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.16.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.16.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.16.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.16.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.16.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.16.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.16.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.16.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.17.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.17.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.17.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.17.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.17.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.17.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.17.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.17.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.17.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.17.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.17.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.17.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.18.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.18.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.18.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.18.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.18.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.18.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.18.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.18.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.18.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.18.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.18.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.18.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.19.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.19.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.19.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.19.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.19.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.19.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.19.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.19.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.19.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.19.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.19.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.19.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.2.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.2.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.2.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.2.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.2.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.2.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.2.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.2.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.2.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.2.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.2.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.2.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.20.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.20.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.20.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.20.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.20.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.20.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.20.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.20.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.20.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.20.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.20.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.20.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.21.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.21.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.21.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.21.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.21.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.21.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.21.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.21.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.21.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.21.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.21.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.21.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.22.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.22.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.22.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.22.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.22.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.22.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.22.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.22.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.22.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.22.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.22.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.22.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.23.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.23.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.23.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.23.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.23.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.23.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.23.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.23.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.23.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.23.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.23.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.23.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.3.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.3.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.3.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.3.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.3.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.3.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.3.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.3.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.3.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.3.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.3.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.3.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.4.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.4.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.4.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.4.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.4.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.4.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.4.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.4.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.4.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.4.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.4.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.4.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.5.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.5.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.5.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.5.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.5.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.5.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.5.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.5.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.5.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.5.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.5.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.5.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.6.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.6.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.6.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.6.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.6.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.6.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.6.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.6.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.6.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.6.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.6.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.6.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.7.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.7.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.7.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.7.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.7.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.7.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.7.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.7.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.7.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.7.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.7.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.7.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.8.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.8.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.8.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.8.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.8.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.8.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.8.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.8.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.8.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.8.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.8.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.8.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.9.attention.key.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.9.attention.key.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.9.attention.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.9.attention.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.9.attention.query.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.9.attention.query.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.9.attention.value.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.9.attention.value.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.9.norm1.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.9.norm1.weight": "model-00004-of-00004.safetensors",
    "predictor.layer.9.norm2.bias": "model-00004-of-00004.safetensors",
    "predictor.layer.9.norm2.weight": "model-00004-of-00004.safetensors",
    "predictor.layernorm.bias": "model-00004-of-00004.safetensors",
    "predictor.layernorm.weight": "model-00004-of-00004.safetensors",
    "predictor.proj.bias": "model-00004-of-00004.safetensors",
    "predictor.proj.weight": "model-00004-of-00004.safetensors",
    "predictor.proj_context.bias": "model-00004-of-00004.safetensors",
    "predictor.proj_context.weight": "model-00004-of-00004.safetensors"
  }
}