config.json

{
  "architectures": [
    "Blip2ForImageTextRetrieval"
  ],
  "image_text_hidden_size": 256,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "model_type": "blip-2",
  "num_query_tokens": 32,
  "qformer_config": {
    "model_type": "blip_2_qformer",
    "qformer_text_input": true,
    "vocab_size": 30523
  },
  "torch_dtype": "float32",
  "transformers_version": "4.35.0.dev0",
  "vision_config": {
    "model_type": "blip_2_vision_model"
  }
}