config.json

{
  "_name_or_path": "Salesforce/blip-image-captioning-base",
  "architectures": [
    "BlipForConditionalGeneration"
  ],
  "decoder_start_token_id": 101,
  "image_text_hidden_size": 256,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "logit_scale_init_value": 2.6592,
  "max_length": 120,
  "model_type": "blip",
  "pad_token_id": 0,
  "projection_dim": 512,
  "text_config": {
    "initializer_factor": 1.0,
    "model_type": "blip_text_model",
    "num_attention_heads": 12
  },
  "torch_dtype": "float32",
  "transformers_version": "4.36.2",
  "vision_config": {
    "dropout": 0.0,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "model_type": "blip_vision_model",
    "num_channels": 3
  }
}