model.safetensors.index.json

{
  "metadata": {
    "total_size": 19164356362
  },
  "weight_map": {
    "lm_head.weight": "model-00004-of-00004.safetensors",
    "model.audio_projector.0.bias": "model-00004-of-00004.safetensors",
    "model.audio_projector.0.weight": "model-00004-of-00004.safetensors",
    "model.audio_projector.2.bias": "model-00004-of-00004.safetensors",
    "model.audio_projector.2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.classifier.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.classifier.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.conv1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.conv1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.conv2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.conv2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.embed_positions.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.0.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.1.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.10.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.11.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.12.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.13.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.14.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.15.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.16.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.17.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.18.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.19.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.2.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.20.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.21.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.22.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.23.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.24.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.25.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.26.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.27.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.28.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.29.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.3.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.30.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.31.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.4.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.5.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.6.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.7.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.8.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.fc1.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.fc1.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.fc2.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.fc2.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.final_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.final_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.encoder.layers.9.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.projector.bias": "model-00004-of-00004.safetensors",
    "model.audio_tower.audio_tower.projector.weight": "model-00004-of-00004.safetensors",
    "model.bert_gate.0.bias": "model-00004-of-00004.safetensors",
    "model.bert_gate.0.weight": "model-00004-of-00004.safetensors",
    "model.bert_gate.2.bias": "model-00004-of-00004.safetensors",
    "model.bert_gate.2.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.embeddings.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.embeddings.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.embeddings.position_embeddings.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.embeddings.token_type_embeddings.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.embeddings.word_embeddings.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.0.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.1.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.10.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.11.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.2.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.3.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.4.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.5.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.6.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.7.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.8.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.self.key.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.self.key.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.self.query.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.self.query.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.self.value.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.attention.self.value.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.intermediate.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.intermediate.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.output.LayerNorm.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.output.LayerNorm.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.output.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.encoder.layer.9.output.dense.weight": "model-00004-of-00004.safetensors",
    "model.bert_model.pooler.dense.bias": "model-00004-of-00004.safetensors",
    "model.bert_model.pooler.dense.weight": "model-00004-of-00004.safetensors",
    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
    "model.feature_compressor.vlm_key_projector.bias": "model-00004-of-00004.safetensors",
    "model.feature_compressor.vlm_key_projector.weight": "model-00004-of-00004.safetensors",
    "model.feature_compressor.vlm_query_projector.bias": "model-00004-of-00004.safetensors",
    "model.feature_compressor.vlm_query_projector.weight": "model-00004-of-00004.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.mm_projector.mlp_2xgelu_face.0.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.mlp_2xgelu_face.0.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.mlp_2xgelu_face.2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.mlp_2xgelu_face.2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.readout_body.0.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.readout_body.0.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.readout_body.2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.readout_body.2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.readout_video.0.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.readout_video.0.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.readout_video.2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.readout_video.2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.downsample.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.downsample.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.downsample.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b1.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b2.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b3.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_body.b4.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.downsample.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.downsample.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.downsample.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b1.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b2.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b3.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s1_video.b4.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b1.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b2.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b3.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_body.b4.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b1.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b2.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b3.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.conv1.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.conv1.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.conv1.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.conv2.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.conv2.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.conv2.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.conv3.bn.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.conv3.bn.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.conv3.conv.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.se.fc1.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.se.fc1.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.se.fc2.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.s2_video.b4.se.fc2.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.sampler_body.0.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.sampler_body.0.weight": "model-00004-of-00004.safetensors",
    "model.mm_projector.sampler_video.0.bias": "model-00004-of-00004.safetensors",
    "model.mm_projector.sampler_video.0.weight": "model-00004-of-00004.safetensors",
    "model.norm.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.attention.in_proj_bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.attention.in_proj_weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.attention.out_proj.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.attention.out_proj.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.layernorm.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.layernorm.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.mlp.fc1.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.mlp.fc1.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.mlp.fc2.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.mlp.fc2.weight": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.head.probe": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
  }
}