config.json

{
  "_name_or_path": "OFA-Sys/chinese-clip-vit-large-patch14",
  "architectures": [
    "ChineseCLIPDualTextModel"
  ],
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "logit_scale_init_value": 2.6592,
  "model_type": "chinese_clip",
  "projection_dim": 768,
  "text_config": {
    "architectures": [
      "ChineseCLIPTextModel"
    ],
    "bos_token_id": 0,
    "directionality": "bidi",
    "eos_token_id": 2,
    "model_type": "chinese_clip_text_model",
    "output_past": true,
    "pooler_fc_size": 768,
    "pooler_num_attention_heads": 12,
    "pooler_num_fc_layers": 3,
    "pooler_size_per_head": 128,
    "pooler_type": "first_token_transform",
    "vocab_size": 21128
  },
  "torch_dtype": "float32",
  "transformers_version": "4.42.3",
  "vision_config": {
    "dropout": 0.0,
    "hidden_size": 1024,
    "intermediate_size": 4096,
    "model_type": "chinese_clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768
  }
}