transformers/config.json

{
  "model_type": "clip",
  "text_config": {
    "model_type": "clip_text_model",
    "hidden_size": 768,
    "intermediate_size": 3072,
    "max_position_embeddings": 248,
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "vocab_size": 49408,
    "projection_dim": 768,
    "hidden_act": "quick_gelu",
    "layer_norm_eps": 1e-05,
    "attention_dropout": 0.0,
    "dropout": 0.0
  },
  "vision_config": {
    "model_type": "clip_vision_model",
    "hidden_size": 1024,
    "intermediate_size": 4096,
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "image_size": 224,
    "projection_dim": 768,
    "num_channels": 3,
    "hidden_act": "quick_gelu",
    "layer_norm_eps": 1e-05,
    "attention_dropout": 0.0,
    "dropout": 0.0
  },
  "projection_dim": 768,
  "logit_scale_init_value": 2.6592,
  "initializer_factor": 1.0,
  "dtype": "float32",
  "architectures": [
    "CLIPModel"
  ],
  "transformers_version": "4.57.3"
}