{
    "metadata": {
        "total_size": 605109760
    },
    "weight_map": {
        "logit_scale": "model.safetensors",
        "text_model.embeddings.position_embedding.weight": "model.safetensors",
        "text_model.embeddings.position_ids": "model.safetensors",
        "text_model.embeddings.token_embedding.weight": "model.safetensors",
        "text_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
        "text_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
        "text_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
        "text_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
        "text_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
        "text_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
        "text_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
        "text_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
        "text_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
        "text_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
        "text_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
        "text_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
        "text_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
        "text_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
        "text_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
        "text_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
        "text_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
        "text_model.final_layer_norm.bias": "model.safetensors",
        "text_model.final_layer_norm.weight": "model.safetensors",
        "text_projection.weight": "model.safetensors",
        "vision_model.embeddings.class_embedding": "model.safetensors",
        "vision_model.embeddings.patch_embedding.weight": "model.safetensors",
        "vision_model.embeddings.position_embedding.weight": "model.safetensors",
        "vision_model.embeddings.position_ids": "model.safetensors",
        "vision_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
        "vision_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
        "vision_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
        "vision_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
        "vision_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
        "vision_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
        "vision_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
        "vision_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
        "vision_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
        "vision_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
        "vision_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
        "vision_model.post_layernorm.bias": "model.safetensors",
        "vision_model.post_layernorm.weight": "model.safetensors",
        "vision_model.pre_layrnorm.bias": "model.safetensors",
        "vision_model.pre_layrnorm.weight": "model.safetensors",
        "visual_projection.weight": "model.safetensors"
    }
}