model.safetensors.index.json

{
  "metadata": {
    "total_size": 5345836068
  },
  "weight_map": {
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.conv1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.conv1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.conv2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.conv2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.embed_positions.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_encoder.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
    "audio_tower.audio_joint_encoder_segmenter.audio_segmenter.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.0._codebook.cluster_size": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.0._codebook.embed": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.0._codebook.embed_avg": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.0._codebook.initted": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.1._codebook.cluster_size": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.1._codebook.embed": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.1._codebook.embed_avg": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.1._codebook.initted": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.2._codebook.cluster_size": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.2._codebook.embed": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.2._codebook.embed_avg": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.2._codebook.initted": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.3._codebook.cluster_size": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.3._codebook.embed": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.3._codebook.embed_avg": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.layers.3._codebook.initted": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.0.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.0.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.0.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.0.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.1.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.1.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.1.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.1.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.2.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.2.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.2.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.2.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.3.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.3.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.3.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.layers.3.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.proj_in.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.0.proj_in.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.0.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.0.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.0.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.0.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.1.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.1.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.1.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.1.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.2.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.2.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.2.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.2.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.3.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.3.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.3.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.layers.3.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.proj_in.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.1.proj_in.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.0.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.0.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.0.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.0.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.1.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.1.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.1.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.1.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.2.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.2.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.2.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.2.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.3.0.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.3.0.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.3.2.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.layers.3.2.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.proj_in.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.mlps.2.proj_in.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.project_in.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.project_in.weight": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.project_out.bias": "model-00001-of-00002.safetensors",
    "audio_tower.vq.rvq.project_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_embed_affine_layer.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_embed_affine_layer.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.after_norm.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.after_norm.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.embed.out.0.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.embed.out.0.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.embed.out.1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.embed.out.1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.norm_ff.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.norm_ff.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.norm_mha.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.norm_mha.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.0.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.norm_ff.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.norm_ff.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.norm_mha.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.norm_mha.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder.encoders.1.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder_affine_layer.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.audio_token_encoder_affine_layer.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.fuse_encoded_audio_text_module.weights": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.after_norm.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.after_norm.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.embed.out.0.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.embed.out.0.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.embed.out.1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.embed.out.1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.norm1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.norm1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.norm2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.norm2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.0.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.norm1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.norm1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.norm2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.norm2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.1.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.norm1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.norm1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.norm2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.norm2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.2.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.norm1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.norm1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.norm2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.norm2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.3.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.norm1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.norm1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.norm2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.norm2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.4.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.norm1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.norm1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.norm2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.norm2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.5.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.norm1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.norm1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.norm2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.norm2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.llm.encoders.6.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.llm_decoder.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.llm_decoder.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.llm_embedding.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.speech_embedding.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.spk_embed_affine_layer.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.spk_embed_affine_layer.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_embedding.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.after_norm.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.after_norm.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.embed.out.0.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.embed.out.0.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.embed.out.1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.embed.out.1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.norm_ff.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.norm_ff.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.norm_mha.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.norm_mha.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.0.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.norm_ff.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.norm_ff.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.norm_mha.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.norm_mha.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.1.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.feed_forward.w_1.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.feed_forward.w_1.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.feed_forward.w_2.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.feed_forward.w_2.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.norm_ff.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.norm_ff.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.norm_mha.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.norm_mha.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.linear_k.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.linear_k.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.linear_out.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.linear_out.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.linear_pos.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.linear_q.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.linear_q.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.linear_v.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.linear_v.weight": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.pos_bias_u": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder.encoders.2.self_attn.pos_bias_v": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder_affine_layer.bias": "model-00001-of-00002.safetensors",
    "speech_decoder.text_encoder_affine_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.extract_for_bridge_out_llm.linear.bias": "model-00002-of-00002.safetensors",
    "spoken_lm.extract_for_bridge_out_llm.linear.weight": "model-00002-of-00002.safetensors",
    "spoken_lm.fuse_for_bridge_in_llm.linear.bias": "model-00001-of-00002.safetensors",
    "spoken_lm.fuse_for_bridge_in_llm.linear.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.fuse_for_bridge_in_llm.weights": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.lm_head.weight": "model-00002-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.language_model.base_model.model.model.norm.weight": "model-00001-of-00002.safetensors",
    "spoken_lm.pad_audio_unit_embed": "model-00001-of-00002.safetensors",
    "spoken_lm.pad_text_unit_embed": "model-00001-of-00002.safetensors"
  }
}