{
  "metadata": {
    "total_size": 5760316620
  },
  "weight_map": {
    "logit_scale": "model-00001-of-00002.safetensors",
    "text_model.embeddings.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.embeddings.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.embeddings.position_embeddings.weight": "model-00001-of-00002.safetensors",
    "text_model.embeddings.token_type_embeddings.weight": "model-00001-of-00002.safetensors",
    "text_model.embeddings.word_embeddings.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.self.value.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.attention.self.value.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.self.value.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.attention.self.value.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.10.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.11.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.12.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.13.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.14.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.15.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.16.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.17.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.18.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.19.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.self.value.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.attention.self.value.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.20.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.21.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.22.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.self.key.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.self.key.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.self.query.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.self.query.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.23.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.self.value.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.attention.self.value.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.3.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.self.value.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.attention.self.value.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.4.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.self.value.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.attention.self.value.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.5.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.self.value.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.attention.self.value.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.6.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.self.value.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.attention.self.value.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.7.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.self.value.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.attention.self.value.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.output.dense.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.8.output.dense.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.self.key.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.self.key.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.self.query.bias": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.self.query.weight": "model-00001-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.self.value.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.attention.self.value.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.output.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.encoder.layer.9.output.dense.weight": "model-00002-of-00002.safetensors",
    "text_model.pooler.dense.bias": "model-00002-of-00002.safetensors",
    "text_model.pooler.dense.weight": "model-00002-of-00002.safetensors",
    "text_projection.weight": "model-00002-of-00002.safetensors",
    "vision_model.logit_bias": "model-00001-of-00002.safetensors",
    "vision_model.logit_scale": "model-00001-of-00002.safetensors",
    "vision_model.text_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.embeddings.token_embedding.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.final_layer_norm.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.final_layer_norm.weight": "model-00001-of-00002.safetensors",
    "vision_model.text_model.head.bias": "model-00001-of-00002.safetensors",
    "vision_model.text_model.head.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
    "vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors",
    "visual_projection.weight": "model-00002-of-00002.safetensors"
  }
}