{
  "architectures": [
    "ImageQFormerModel"
  ],
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "model_type": "blip-2",
  "num_query_tokens": 32,
  "qformer_config": {
    "model_type": "blip_2_qformer"
  },
  "text_config": {
    "model_type": "opt"
  },
  "torch_dtype": "float32",
  "transformers_version": "4.34.1",
  "use_decoder_only_language_model": true,
  "vision_config": {
    "model_type": "blip_2_vision_model"
  }
}