config.json

{
  "architectures": [
    "ImageQFormerModel"
  ],
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "model_type": "blip-2",
  "num_query_tokens": 32,
  "qformer_config": {
    "architectures": [
      "Blip2QFormerModel"
    ],
    "num_query_tokens": 32,
    "attention_probs_dropout_prob": 0.1,
    "classifier_dropout": null,
    "cross_attention_frequency": 2,
    "encoder_hidden_size": 1408,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-12,
    "max_position_embeddings": 512,
    "model_type": "blip_2_qformer",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "pad_token_id": 0,
    "position_embedding_type": "absolute",
    "torch_dtype": "float32",
    "transformers_version": "4.34.1",
    "vocab_size": 30522
  },
  "torch_dtype": "float32",
  "transformers_version": "4.34.1",
  "vision_config": {
    "architectures": [
      "Blip2VisionModel"
    ],
    "attention_dropout": 0.0,
    "dropout": 0.0,
    "hidden_act": "gelu",
    "hidden_size": 1408,
    "image_size": 224,
    "initializer_factor": 1.0,
    "initializer_range": 1e-10,
    "intermediate_size": 6144,
    "layer_norm_eps": 1e-06,
    "model_type": "blip_2_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 39,
    "patch_size": 14,
    "projection_dim": 512,
    "qkv_bias": true,
    "torch_dtype": "float32",
    "transformers_version": "4.34.1"
  }
}