config.json

{
  "architectures": [
    "Blip2ForConditionalGeneration"
  ],
  "image_text_hidden_size": 256,
  "image_token_index": 50265,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "model_type": "blip-2",
  "num_query_tokens": 32,
  "qformer_config": {
    "classifier_dropout": null,
    "model_type": "blip_2_qformer"
  },
  "text_config": {
    "activation_dropout": 0.0,
    "architectures": [
      "OPTForCausalLM"
    ],
    "eos_token_id": 50118,
    "ffn_dim": 16384,
    "hidden_size": 4096,
    "model_type": "opt",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "prefix": "</s>",
    "torch_dtype": "float16",
    "vocab_size": 50304,
    "word_embed_proj_dim": 4096
  },
  "torch_dtype": "float32",
  "transformers_version": "4.47.0.dev0",
  "use_decoder_only_language_model": true,
  "vision_config": {
    "dropout": 0.0,
    "image_size": 364,
    "initializer_factor": 1.0,
    "model_type": "blip_2_vision_model",
    "num_channels": 3,
    "projection_dim": 512
  }
}