{
  "metadata": {
    "total_size": 143040912384
  },
  "weight_map": {
    "audio_adapter.output_projector.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.output_projector.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.pre_qformer_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.pre_qformer_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.embeddings.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.embeddings.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.embeddings.position_ids": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.output.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.output.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.output.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.output.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.self.key.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.self.key.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.self.query.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.self.query.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.self.value.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.attention.self.value.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.output.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.output.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.self.key.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.self.key.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.self.query.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.self.query.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.self.value.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.crossattention.self.value.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.intermediate_query.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.intermediate_query.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.output_query.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.output_query.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.output_query.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.0.output_query.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.output.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.output.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.output.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.output.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.self.key.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.self.key.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.self.query.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.self.query.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.self.value.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.attention.self.value.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.output.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.output.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.output.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.output.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.self.key.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.self.key.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.self.query.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.self.query.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.self.value.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.crossattention.self.value.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.intermediate_query.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.intermediate_query.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.output_query.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.output_query.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.output_query.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.1.output_query.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.output.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.output.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.output.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.output.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.self.key.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.self.key.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.self.query.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.self.query.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.self.value.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.attention.self.value.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.output.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.output.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.output.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.output.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.self.key.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.self.key.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.self.query.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.self.query.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.self.value.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.crossattention.self.value.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.intermediate_query.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.intermediate_query.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.output_query.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.output_query.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.output_query.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.2.output_query.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.output.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.output.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.output.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.output.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.self.key.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.self.key.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.self.query.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.self.query.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.self.value.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.attention.self.value.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.output.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.output.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.output.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.output.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.self.key.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.self.key.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.self.query.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.self.query.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.self.value.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.crossattention.self.value.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.intermediate_query.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.intermediate_query.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.output_query.LayerNorm.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.output_query.LayerNorm.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.output_query.dense.bias": "model-00030-of-00030.safetensors",
    "audio_adapter.qformer.encoder.layer.3.output_query.dense.weight": "model-00030-of-00030.safetensors",
    "audio_adapter.query_embeds": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.ffn.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.ffn.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.ffn.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.ffn.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.ffn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.ffn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.residual_conv.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.residual_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.residual_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.residual_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn_conv.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.adapter.layers.0.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.0.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.1.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.10.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.11.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.12.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.13.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.14.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.15.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.16.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.17.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.18.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.19.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.2.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.20.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.21.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.22.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.23.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.3.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.4.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.5.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.6.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.7.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.8.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.conv_module.depthwise_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.conv_module.depthwise_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.conv_module.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.conv_module.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.conv_module.pointwise_conv1.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.conv_module.pointwise_conv2.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn1.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn1.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn1.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn1.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn1_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn1_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn2.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn2.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn2.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn2.output_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn2_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.ffn2_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.final_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.final_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn.distance_embedding.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.encoder.layers.9.self_attn_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.feature_projection.layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.feature_projection.layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.feature_projection.projection.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.feature_projection.projection.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.inner_layer_norm.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.inner_layer_norm.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.intermediate_ffn.intermediate_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.intermediate_ffn.intermediate_dense.weight": "model-00030-of-00030.safetensors",
    "audio_encoder.model.intermediate_ffn.output_dense.bias": "model-00030-of-00030.safetensors",
    "audio_encoder.model.intermediate_ffn.output_dense.weight": "model-00030-of-00030.safetensors",
    "text_decoder.model.lm_head.weight": "model-00030-of-00030.safetensors",
    "text_decoder.model.model.embed_tokens.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
    "text_decoder.model.model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.12.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.12.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
    "text_decoder.model.model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.15.input_layernorm.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.15.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
    "text_decoder.model.model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.16.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.16.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.16.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.18.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.18.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
    "text_decoder.model.model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.19.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.21.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.21.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.21.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
    "text_decoder.model.model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
    "text_decoder.model.model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.24.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.24.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.24.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.24.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.24.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.26.input_layernorm.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.26.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.26.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.26.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
    "text_decoder.model.model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.27.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.27.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.27.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.27.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.29.input_layernorm.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.29.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.29.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.29.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.29.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
    "text_decoder.model.model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.30.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.32.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.32.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
    "text_decoder.model.model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.35.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.35.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
    "text_decoder.model.model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
    "text_decoder.model.model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.38.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.38.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.38.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.38.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.4.input_layernorm.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.4.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.4.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.4.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
    "text_decoder.model.model.layers.40.input_layernorm.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.40.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.40.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.40.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
    "text_decoder.model.model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.41.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.43.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.43.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
    "text_decoder.model.model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.46.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
    "text_decoder.model.model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.49.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
    "text_decoder.model.model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
    "text_decoder.model.model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.52.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.54.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
    "text_decoder.model.model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.57.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
    "text_decoder.model.model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
    "text_decoder.model.model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.63.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.63.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
    "text_decoder.model.model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.65.input_layernorm.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.65.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.65.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
    "text_decoder.model.model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.68.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
    "text_decoder.model.model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.7.input_layernorm.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.7.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.7.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.7.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.7.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
    "text_decoder.model.model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.71.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
    "text_decoder.model.model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.74.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.74.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
    "text_decoder.model.model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.77.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.77.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.77.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
    "text_decoder.model.model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.79.input_layernorm.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.79.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.79.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
    "text_decoder.model.model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.8.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
    "text_decoder.model.model.norm.weight": "model-00029-of-00030.safetensors",
    "video_adapter.layers.0.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.0.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.1.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.1.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.10.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.10.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.12.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.12.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.13.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.13.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.15.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.15.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.16.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.16.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.3.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.3.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.4.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.4.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.6.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.6.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.7.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.7.weight": "model-00030-of-00030.safetensors",
    "video_adapter.layers.9.bias": "model-00030-of-00030.safetensors",
    "video_adapter.layers.9.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.after_norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.after_norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.embed.0.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.embed.0.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.0.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.1.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.10.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.11.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.2.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.3.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.4.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.5.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.6.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.7.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.8.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.depthwise_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.depthwise_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.norm.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.norm.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.norm.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.norm.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.norm.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.pointwise_cov1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.pointwise_cov1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.pointwise_cov2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.conv_module.pointwise_cov2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.feed_forward.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.feed_forward.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.feed_forward.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.feed_forward.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.feed_forward_macaron.w_1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.feed_forward_macaron.w_1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.feed_forward_macaron.w_2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.feed_forward_macaron.w_2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_conv.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_conv.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_ff.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_ff.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_ff_macaron.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_ff_macaron.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_final.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_final.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_mha.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.norm_mha.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.linear_k.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.linear_k.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.linear_out.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.linear_out.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.linear_pos.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.linear_q.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.linear_q.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.linear_v.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.linear_v.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.pos_bias_u": "model-00030-of-00030.safetensors",
    "video_encoder.model.encoders.9.self_attn.pos_bias_v": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.frontend3D.0.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.frontend3D.1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.frontend3D.1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.frontend3D.1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.frontend3D.1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.frontend3D.1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn2.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn2.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn2.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.bn2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.conv1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.0.conv2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn2.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn2.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn2.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.bn2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.conv1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer1.1.conv2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn2.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn2.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn2.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.bn2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.conv1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.conv2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.downsample.0.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.downsample.1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.downsample.1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.downsample.1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.downsample.1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.0.downsample.1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn2.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn2.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn2.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.bn2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.conv1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer2.1.conv2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn2.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn2.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn2.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.bn2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.conv1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.conv2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.downsample.0.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.downsample.1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.downsample.1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.downsample.1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.downsample.1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.0.downsample.1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn2.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn2.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn2.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.bn2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.conv1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer3.1.conv2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn2.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn2.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn2.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.bn2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.conv1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.conv2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.downsample.0.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.downsample.1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.downsample.1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.downsample.1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.downsample.1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.0.downsample.1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn1.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn1.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn1.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn1.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn2.bias": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn2.num_batches_tracked": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn2.running_mean": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn2.running_var": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.bn2.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.conv1.weight": "model-00030-of-00030.safetensors",
    "video_encoder.model.frontend.trunk.layer4.1.conv2.weight": "model-00030-of-00030.safetensors"
  }
}