{
  "architectures": [
    "AestheticPredictor"
  ],
  "auto_map": {
    "AutoConfig": "modeling_aesthetic.AestheticConfig",
    "AutoModel": "modeling_aesthetic.AestheticPredictor"
  },
  "clip_config": {
    "_name_or_path": "openai/clip-vit-large-patch14",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.0,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "dropout": 0.0,
    "dtype": "float32",
    "eos_token_id": null,
    "finetuning_task": null,
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 224,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "output_attentions": false,
    "output_hidden_states": false,
    "pad_token_id": null,
    "patch_size": 14,
    "prefix": null,
    "problem_type": null,
    "projection_dim": 768,
    "pruned_heads": {},
    "return_dict": true,
    "sep_token_id": null,
    "task_specific_params": null,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "torchscript": false,
    "transformers_version": "5.16.1",
    "use_bfloat16": false
  },
  "dtype": "float32",
  "embed_dim": 768,
  "model_type": "aesthetic_predictor",
  "transformers_version": "5.16.1"
}