config.json

{
  "_name_or_path": "/root/.cache/huggingface/hub/Clip-Roco_Version2_v3",
  "architectures": [
    "CLIPModel"
  ],
  "initializer_factor": 1.0,
  "logit_scale_init_value": 2.6592,
  "model_type": "clip",
  "projection_dim": 512,
  "text_config": {
    "_name_or_path": "/kaggle/working/TextModel",
    "architectures": [
      "RobertaModel"
    ],
    "attention_probs_dropout_prob": 0.1,
    "bos_token_id": 0,
    "classifier_dropout": null,
    "eos_token_id": 2,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "intermediate_size": 3072,
    "max_position_embeddings": 1026,
    "model_type": "clip_text_model",
    "num_attention_heads": 12,
    "position_embedding_type": "absolute",
    "torch_dtype": "float32",
    "type_vocab_size": 1,
    "use_cache": true,
    "vocab_size": 50265
  },
  "torch_dtype": "float32",
  "transformers_version": "4.42.3",
  "vision_config": {
    "_name_or_path": "openai/clip-vit-large-patch14-336",
    "dropout": 0.0,
    "hidden_size": 1024,
    "image_size": 336,
    "intermediate_size": 4096,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768
  }
}