diff --git "a/llava_mae/pytorch_model.bin.index.json" "b/llava_mae/pytorch_model.bin.index.json" new file mode 100644--- /dev/null +++ "b/llava_mae/pytorch_model.bin.index.json" @@ -0,0 +1,1590 @@ +{ + "metadata": { + "total_size": 27976926208 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_mm_projector.0.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_mm_projector.0.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_mm_projector.2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_mm_projector.2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.clip_vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.embeddings.cls_token": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.embeddings.patch_embeddings.projection.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.embeddings.patch_embeddings.projection.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.embeddings.position_embeddings": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.0.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.1.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.10.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.11.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.12.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.13.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.14.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.15.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.16.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.17.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.18.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.19.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.2.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.20.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.21.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.22.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.23.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.3.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.4.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.5.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.6.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.7.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.8.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.attention.attention.key.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.attention.attention.key.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.attention.attention.query.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.attention.attention.query.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.attention.attention.value.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.attention.attention.value.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.layernorm_after.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.layernorm_after.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.layernorm_before.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.layernorm_before.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.output.dense.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.encoder.layer.9.output.dense.weight": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.layernorm.bias": "pytorch_model-00003-of-00003.bin", + "model.dino_tower.vision_tower.layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.mm_projector.0.bias": "pytorch_model-00003-of-00003.bin", + "model.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin", + "model.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin", + "model.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin", + "model.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin" + } +}