{
  "metadata": {
    "total_size": 42966658080
  },
  "weight_map": {
    "model.audio_model.conv1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.conv1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.conv2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.conv2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.embed_positions.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.0.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.1.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.10.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.11.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.12.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.13.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.14.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.15.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.16.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.17.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.18.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.19.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.2.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.20.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.21.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.22.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.23.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.24.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.25.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.26.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.27.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.28.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.29.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.3.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.30.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.31.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.4.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.5.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.6.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.7.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.8.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.fc1.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.fc1.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.fc2.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.fc2.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.final_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.final_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.self_attn.out_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.self_attn.out_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.self_attn_layer_norm.bias": "model-00002-of-00010.safetensors",
    "model.audio_model.layers.9.self_attn_layer_norm.weight": "model-00002-of-00010.safetensors",
    "model.audio_projector.fc1.bias": "model-00010-of-00010.safetensors",
    "model.audio_projector.fc1.weight": "model-00010-of-00010.safetensors",
    "model.audio_projector.fc2.bias": "model-00010-of-00010.safetensors",
    "model.audio_projector.fc2.weight": "model-00010-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn.fsmn_block.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn.key.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn.out.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn.out.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn.query.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn.query.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn.value.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn.value.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.attn_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.mlp.0.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.mlp.0.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.mlp.2.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.mlp.2.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.mlp_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.0.mlp_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn.fsmn_block.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn.key.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn.out.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn.out.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn.query.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn.query.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn.value.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn.value.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.attn_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.mlp.0.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.mlp.0.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.mlp.2.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.mlp.2.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.mlp_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.1.mlp_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn.fsmn_block.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn.key.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn.out.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn.out.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn.query.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn.query.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn.value.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn.value.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.attn_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.mlp.0.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.mlp.0.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.mlp.2.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.mlp.2.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.mlp_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.2.mlp_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn.fsmn_block.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn.key.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn.out.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn.out.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn.query.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn.query.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn.value.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn.value.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.attn_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.mlp.0.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.mlp.0.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.mlp.2.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.mlp.2.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.mlp_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.3.mlp_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn.fsmn_block.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn.key.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn.out.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn.out.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn.query.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn.query.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn.value.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn.value.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.attn_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.mlp.0.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.mlp.0.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.mlp.2.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.mlp.2.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.mlp_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.4.mlp_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn.fsmn_block.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn.key.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn.out.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn.out.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn.query.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn.query.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn.value.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn.value.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.attn_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.mlp.0.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.mlp.0.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.mlp.2.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.mlp.2.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.mlp_ln.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.blocks.5.mlp_ln.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.conv1.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.conv1.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.conv2.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.encoder.conv2.weight": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.quantizer._codebook.project_down.bias": "model-00002-of-00010.safetensors",
    "model.discrete_audio_model.quantizer._codebook.project_down.weight": "model-00002-of-00010.safetensors",
    "model.discrete_vision_model.bottleneck.in_linear.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.bottleneck.in_linear.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.bottleneck.out_linear.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.bottleneck.out_linear.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.bottleneck.regularizer.embedding.weight": "model-00002-of-00010.safetensors",
    "model.discrete_vision_model.bottleneck.regularizer.embedding_proj.bias": "model-00002-of-00010.safetensors",
    "model.discrete_vision_model.bottleneck.regularizer.embedding_proj.weight": "model-00002-of-00010.safetensors",
    "model.discrete_vision_model.decode_task_layer.0.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decode_task_layer.0.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decode_task_layer.2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decode_task_layer.2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.embeddings.position_embedding.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.attention.in_proj_bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.attention.in_proj_weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.attention.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.attention.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.layernorm.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.layernorm.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.head.probe": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.post_layernorm.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.decoder.vision_model.post_layernorm.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encode_task_layer.0.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encode_task_layer.0.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.embeddings.patch_embedding.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.embeddings.patch_embedding.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.embeddings.position_embedding.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.layer_norm1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.layer_norm1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.layer_norm2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.layer_norm2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.attention.in_proj_bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.attention.in_proj_weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.attention.out_proj.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.attention.out_proj.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.layernorm.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.layernorm.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.mlp.fc1.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.mlp.fc1.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.mlp.fc2.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.mlp.fc2.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.head.probe": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.post_layernorm.bias": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.encoder.post_layernorm.weight": "model-00001-of-00010.safetensors",
    "model.discrete_vision_model.scale_layer.scale": "model-00002-of-00010.safetensors",
    "model.discrete_vision_model.scale_layer.shift": "model-00002-of-00010.safetensors",
    "model.language_model.lm_head.weight": "model-00010-of-00010.safetensors",
    "model.language_model.model.embed_tokens.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.0.input_layernorm.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.0.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.0.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.1.input_layernorm.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.1.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.1.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.10.input_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.10.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.10.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.11.input_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.11.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.11.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.12.input_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.12.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.12.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.12.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.12.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.12.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.12.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.12.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.12.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.13.input_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.13.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.13.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.13.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.13.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.13.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.13.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.13.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.13.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.14.input_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.14.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.14.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.14.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.14.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.14.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.14.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.14.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.14.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.15.input_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.15.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.15.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.15.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.15.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.15.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.15.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.15.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.15.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.16.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.16.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.16.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.16.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.16.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.16.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.16.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.16.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.17.input_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.17.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.17.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.17.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.17.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.17.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.17.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.17.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.17.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.18.input_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.18.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.18.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.18.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.18.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.18.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.18.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.18.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.18.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.19.input_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.19.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.19.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.19.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.19.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.19.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.19.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.19.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.19.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
    "model.language_model.model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.20.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.20.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.20.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.20.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.20.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.21.input_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.21.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.21.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.21.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.21.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
    "model.language_model.model.layers.22.input_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.22.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.22.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.22.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.22.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.22.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.22.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.22.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.22.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.23.input_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.23.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.23.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.23.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.23.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.23.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.23.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.23.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.23.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.24.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.24.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.24.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.24.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.24.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.24.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.27.input_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.27.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.27.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.27.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
    "model.language_model.model.layers.28.input_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.28.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.28.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.28.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.28.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.28.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.28.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.28.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.28.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.29.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.29.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.29.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.29.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.3.input_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.3.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.3.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.33.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
    "model.language_model.model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
    "model.language_model.model.layers.4.input_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.4.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.4.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.5.input_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.5.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.5.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.6.input_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.6.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.6.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.7.input_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.7.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.7.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.8.input_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.8.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.8.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
    "model.language_model.model.layers.9.input_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.9.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.9.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
    "model.language_model.model.norm.weight": "model-00009-of-00010.safetensors",
    "model.mm_projector.bias": "model-00010-of-00010.safetensors",
    "model.mm_projector.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.input_norm.bias": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.input_norm.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.input_proj.bias": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.input_proj.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.gate_fc.bias": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.gate_fc.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.mixer.A_log": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.mixer.D": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.mixer.conv1d.bias": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.mixer.conv1d.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.mixer.dt_bias": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.mixer.in_proj.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.mixer.norm.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.mixer.out_proj.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.norm.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.weight_fc.bias": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.layers.0.weight_fc.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.model.norm_f.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.output_proj.bias": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.output_proj.weight": "model-00010-of-00010.safetensors",
    "model.video_audio_compressor.query_token": "model-00010-of-00010.safetensors",
    "model.vision_model.blocks.0.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.0.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.1.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.10.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.11.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.12.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.13.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.14.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.15.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.16.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.17.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.18.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.19.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.2.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.20.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.21.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.22.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.23.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.24.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.25.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.26.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.27.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.28.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.29.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.3.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.30.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.31.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.4.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.5.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.6.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.7.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.8.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.attn.proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.attn.proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.attn.qkv.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.attn.qkv.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.norm1.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.blocks.9.norm2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.merger.ln_q.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.merger.mlp.0.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.merger.mlp.0.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.merger.mlp.2.bias": "model-00001-of-00010.safetensors",
    "model.vision_model.merger.mlp.2.weight": "model-00001-of-00010.safetensors",
    "model.vision_model.patch_embed.proj.weight": "model-00001-of-00010.safetensors"
  }
}