POINTS-Yi-1-5-9B-Chat / model.safetensors.index.json
YuanLiuuuuuu's picture
Add files using upload-large-folder tool
e28b279 verified
raw
history blame
110 kB
{
"metadata": {
"total_size": 37879939072
},
"weight_map": {
"general_vit.vision_model.embeddings.class_embedding": "model-00001-of-00008.safetensors",
"general_vit.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.embeddings.position_embedding.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.post_layernorm.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.post_layernorm.weight": "model-00001-of-00008.safetensors",
"general_vit.vision_model.pre_layrnorm.bias": "model-00001-of-00008.safetensors",
"general_vit.vision_model.pre_layrnorm.weight": "model-00001-of-00008.safetensors",
"llm.embed_out.weight": "model-00008-of-00008.safetensors",
"llm.lm.embed_in.weight": "model-00001-of-00008.safetensors",
"llm.lm.final_layer_norm.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.0.attention.dense.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.0.attention.key_value_dense.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.0.attention.query_dense.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.1.attention.dense.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.1.attention.key_value_dense.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.1.attention.query_dense.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.10.attention.dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.10.attention.key_value_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.10.attention.query_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.11.attention.dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.11.attention.key_value_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.11.attention.query_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.12.attention.dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.12.attention.key_value_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.12.attention.query_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.13.attention.dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.13.attention.key_value_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.13.attention.query_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.13.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.13.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.14.attention.dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.14.attention.key_value_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.14.attention.query_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.15.attention.dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.15.attention.key_value_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.15.attention.query_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.15.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.15.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.16.attention.dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.16.attention.key_value_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.16.attention.query_dense.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.16.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.16.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.17.attention.dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.17.attention.key_value_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.17.attention.query_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.17.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.17.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.18.attention.dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.18.attention.key_value_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.18.attention.query_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.18.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.18.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.19.attention.dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.19.attention.key_value_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.19.attention.query_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.19.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.19.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.2.attention.dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.2.attention.key_value_dense.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.2.attention.query_dense.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"llm.lm.layers.20.attention.dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.20.attention.key_value_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.20.attention.query_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.20.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.20.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.21.attention.dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.21.attention.key_value_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.21.attention.query_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.21.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.21.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.22.attention.dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.22.attention.key_value_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.22.attention.query_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.22.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.22.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.23.attention.dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.23.attention.key_value_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.23.attention.query_dense.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.23.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.23.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"llm.lm.layers.24.attention.dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.24.attention.key_value_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.24.attention.query_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.24.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.24.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.25.attention.dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.25.attention.key_value_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.25.attention.query_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.25.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.25.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.26.attention.dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.26.attention.key_value_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.26.attention.query_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.26.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.26.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.27.attention.dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.27.attention.key_value_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.27.attention.query_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.27.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.27.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.28.attention.dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.28.attention.key_value_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.28.attention.query_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.28.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.28.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.29.attention.dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.29.attention.key_value_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.29.attention.query_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.29.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.29.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.3.attention.dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.3.attention.key_value_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.3.attention.query_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.30.attention.dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.30.attention.key_value_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.30.attention.query_dense.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.30.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.30.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"llm.lm.layers.31.attention.dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.31.attention.key_value_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.31.attention.query_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.31.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.31.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.32.attention.dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.32.attention.key_value_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.32.attention.query_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.32.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.32.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.33.attention.dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.33.attention.key_value_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.33.attention.query_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.33.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.33.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.34.attention.dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.34.attention.key_value_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.34.attention.query_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.34.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.34.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.34.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.35.attention.dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.35.attention.key_value_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.35.attention.query_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.35.input_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.35.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.35.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.35.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.36.attention.dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.36.attention.key_value_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.36.attention.query_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.36.input_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.36.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.36.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.36.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.37.attention.dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.37.attention.key_value_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.37.attention.query_dense.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.37.input_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.37.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.37.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.37.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"llm.lm.layers.38.attention.dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.38.attention.key_value_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.38.attention.query_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.38.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.38.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.39.attention.dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.39.attention.key_value_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.39.attention.query_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.39.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.39.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.4.attention.dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.4.attention.key_value_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.4.attention.query_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.40.attention.dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.40.attention.key_value_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.40.attention.query_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.40.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.40.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.41.attention.dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.41.attention.key_value_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.41.attention.query_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.41.input_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.41.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.41.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.42.attention.dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.42.attention.key_value_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.42.attention.query_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.42.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.42.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.43.attention.dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.43.attention.key_value_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.43.attention.query_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.43.input_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.43.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.43.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.44.attention.dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.44.attention.key_value_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.44.attention.query_dense.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.44.input_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.44.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.44.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"llm.lm.layers.45.attention.dense.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.45.attention.key_value_dense.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.45.attention.query_dense.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.45.input_layernorm.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.45.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.45.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.45.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.46.attention.dense.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.46.attention.key_value_dense.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.46.attention.query_dense.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.46.input_layernorm.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.46.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.46.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.46.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.47.attention.dense.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.47.attention.key_value_dense.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.47.attention.query_dense.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.47.input_layernorm.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.47.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.47.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.47.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
"llm.lm.layers.5.attention.dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.5.attention.key_value_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.5.attention.query_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.6.attention.dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.6.attention.key_value_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.6.attention.query_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.7.attention.dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.7.attention.key_value_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.7.attention.query_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.8.attention.dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.8.attention.key_value_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.8.attention.query_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.9.attention.dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.9.attention.key_value_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.9.attention.query_dense.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
"llm.lm.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"llm.lm.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"ocr_vit.vision_model.embeddings.class_embedding": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.embeddings.position_embedding.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.post_layernorm.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.post_layernorm.weight": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.pre_layrnorm.bias": "model-00001-of-00008.safetensors",
"ocr_vit.vision_model.pre_layrnorm.weight": "model-00001-of-00008.safetensors",
"vision_projector.0.bias": "model-00008-of-00008.safetensors",
"vision_projector.0.weight": "model-00008-of-00008.safetensors",
"vision_projector.2.bias": "model-00008-of-00008.safetensors",
"vision_projector.2.weight": "model-00008-of-00008.safetensors"
}
}