{
  "architectures": [
    "DuoduoCLIPModel"
  ],
  "auto_map": {
    "AutoConfig": "configuration_duoduoclip.DuoduoCLIPConfig",
    "AutoModel": "modeling_duoduoclip.DuoduoCLIPModel"
  },
  "default_num_views": null,
  "dtype": "float32",
  "hf_clip_model_name": "openai/clip-vit-base-patch32",
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "initializer_factor": 1.0,
  "layers_threshold": 6,
  "logit_scale_init_value": 2.6592,
  "model_type": "duoduoclip",
  "projection_dim": 512,
  "text_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu",
    "hidden_size": 512,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 2048,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 77,
    "model_type": "clip_text_model",
    "num_attention_heads": 8,
    "num_hidden_layers": 12,
    "pad_token_id": 49407,
    "projection_dim": 512,
    "vocab_size": 49408
  },
  "transformers_version": "4.57.6",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu",
    "hidden_size": 768,
    "image_size": 224,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 32,
    "projection_dim": 512
  }
}