qformer/config.json

{
  "_name_or_path": "ayushtues/blipdiffusion",
  "architectures": [
    "Blip2QFormerModel"
  ],
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "model_type": "blip-2",
  "num_query_tokens": 16,
  "qformer_config": {
    "cross_attention_frequency": 1,
    "encoder_hidden_size": 1024,
    "model_type": "blip_2_qformer",
    "vocab_size": 30523
  },
  "text_config": {
    "model_type": "opt"
  },
  "torch_dtype": "float32",
  "transformers_version": "4.33.0.dev0",
  "use_decoder_only_language_model": true,
  "vision_config": {
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "intermediate_size": 4096,
    "model_type": "blip_2_vision_model",
    "num_hidden_layers": 23
  }
}