{
  "metadata": {
    "total_size": 18192666972
  },
  "weight_map": {
    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.embeddings.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.embeddings.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.embeddings.position_ids": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.0.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.1.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.10.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.11.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.2.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.3.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.4.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.5.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.6.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.7.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.8.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.Qformer.bert.encoder.layer.9.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.embeddings.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.embeddings.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.embeddings.position_ids": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.0.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_Qformer.bert.encoder.layer.1.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.audio.0.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.audio.0.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.audio.2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.depth.0.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.depth.0.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.depth.2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.imu.0.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.imu.0.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.imu.3.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.text.proj.0.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.text.proj.0.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.text.proj.1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.thermal.0.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.thermal.0.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.thermal.2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.vision.0.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.vision.0.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_heads.vision.2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_postprocessors.audio.1.log_logit_scale": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_postprocessors.depth.1.log_logit_scale": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_postprocessors.imu.1.log_logit_scale": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_postprocessors.text.1.log_logit_scale": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_postprocessors.thermal.1.log_logit_scale": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.audio.cls_token": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.audio.pos_embedding_helper.pos_embed": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.audio.rgbt_stem.norm_layer.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.audio.rgbt_stem.norm_layer.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.audio.rgbt_stem.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.depth.cls_token": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.depth.depth_stem.norm_layer.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.depth.depth_stem.norm_layer.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.depth.depth_stem.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.depth.pos_embedding_helper.pos_embed": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.imu.cls_token": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.imu.imu_stem.norm_layer.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.imu.imu_stem.norm_layer.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.imu.imu_stem.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.imu.pos_embed": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.text.mask": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.text.pos_embed": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.text.token_embedding.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.thermal.cls_token": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.thermal.pos_embedding_helper.pos_embed": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.thermal.rgbt_stem.norm_layer.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.thermal.rgbt_stem.norm_layer.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.thermal.rgbt_stem.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.vision.cls_token": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.vision.pos_embedding_helper.pos_embed": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_preprocessors.vision.rgbt_stem.proj.1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.0.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.1.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.10.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.11.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.2.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.3.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.4.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.5.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.6.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.7.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.8.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.audio.blocks.9.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.0.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.1.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.10.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.11.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.2.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.3.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.4.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.5.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.6.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.7.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.8.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.depth.blocks.9.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.0.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.1.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.2.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.3.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.4.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.imu.blocks.5.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.0.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.1.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.10.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.11.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.12.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.13.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.14.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.15.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.16.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.17.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.18.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.19.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.2.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.20.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.21.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.22.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.23.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.3.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.4.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.5.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.6.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.7.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.8.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.text.blocks.9.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.0.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.1.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.10.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.11.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.2.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.3.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.4.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.5.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.6.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.7.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.8.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.attn.bias_k": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.attn.bias_v": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.thermal.blocks.9.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.0.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.1.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.10.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.11.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.12.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.13.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.14.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.15.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.16.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.17.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.18.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.19.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.2.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.20.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.21.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.22.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.23.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.24.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.25.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.26.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.27.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.28.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.29.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.3.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.30.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.31.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.4.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.5.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.6.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.7.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.8.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.attn.in_proj_bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.attn.in_proj_weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.norm_1.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.norm_1.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.norm_2.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.blocks.9.norm_2.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.pre_transformer_layer.0.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_encoder.modality_trunks.vision.pre_transformer_layer.0.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_llama_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.audio_llama_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_position_embedding.weight": "pytorch_model-00002-of-00002.bin",
    "model.audio_query_tokens": "pytorch_model-00001-of-00002.bin",
    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.llama_proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.llama_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.ln_vision.bias": "pytorch_model-00002-of-00002.bin",
    "model.ln_vision.weight": "pytorch_model-00002-of-00002.bin",
    "model.mm_vision_projector.0.bias": "pytorch_model-00002-of-00002.bin",
    "model.mm_vision_projector.0.weight": "pytorch_model-00002-of-00002.bin",
    "model.mm_vision_projector.2.bias": "pytorch_model-00002-of-00002.bin",
    "model.mm_vision_projector.2.weight": "pytorch_model-00002-of-00002.bin",
    "model.norm.weight": "pytorch_model-00002-of-00002.bin",
    "model.query_tokens": "pytorch_model-00001-of-00002.bin",
    "model.video_Qformer.bert.embeddings.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.embeddings.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.embeddings.position_ids": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.0.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.output.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.output.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.self.key.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.self.key.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.self.query.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.self.query.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.self.value.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.crossattention.self.value.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.output_query.dense.bias": "pytorch_model-00002-of-00002.bin",
    "model.video_Qformer.bert.encoder.layer.1.output_query.dense.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_frame_position_embedding.weight": "pytorch_model-00002-of-00002.bin",
    "model.video_query_tokens": "pytorch_model-00001-of-00002.bin",
    "model.visual_encoder.blocks.0.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.0.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.1.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.10.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.11.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.12.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.13.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.14.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.15.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.16.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.17.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.18.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.19.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.2.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.20.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.21.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.22.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.23.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.24.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.25.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.26.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.27.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.28.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.29.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.3.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.30.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.31.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.32.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.33.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.34.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.35.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.36.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.37.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.38.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.4.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.5.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.6.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.7.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.8.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.attn.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.attn.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.attn.q_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.attn.qkv.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.attn.v_bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.norm1.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.norm1.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.norm2.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.blocks.9.norm2.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.cls_token": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.patch_embed.proj.bias": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.patch_embed.proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.visual_encoder.pos_embed": "pytorch_model-00002-of-00002.bin"
  }
}