{
  "architectures": [
    "Blip2ForConditionalGeneration"
  ],
  "image_text_hidden_size": 256,
  "image_token_index": null,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "model_type": "blip-2",
  "num_query_tokens": 32,
  "qformer_config": {
    "_attn_implementation_autoset": true,
    "encoder_hidden_size": 1024,
    "hidden_size": 1024,
    "model_type": "blip_2_qformer",
    "num_attention_heads": 16
  },
  "text_config": {
    "model_type": "opt"
  },
  "torch_dtype": "float32",
  "transformers_version": "4.47.0",
  "use_decoder_only_language_model": true,
  "vision_config": {
    "_attn_implementation_autoset": true,
    "hidden_size": 1024,
    "image_size": 112,
    "model_type": "blip_2_vision_model",
    "num_hidden_layers": 12,
    "patch_size": 16
  }
}