config.json

{
  "architectures": [
    "MetaClip2ForImageClassification"
  ],
  "dtype": "float32",
  "id2label": {
    "0": "buildings",
    "1": "forest",
    "2": "glacier",
    "3": "mountain",
    "4": "sea",
    "5": "street"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "buildings": 0,
    "forest": 1,
    "glacier": 2,
    "mountain": 3,
    "sea": 4,
    "street": 5
  },
  "logit_scale_init_value": 2.6592,
  "model_type": "metaclip_2",
  "problem_type": "single_label_classification",
  "projection_dim": 384,
  "text_config": {
    "attention_dropout": 0.0,
    "dtype": "float32",
    "eos_token_id": 2,
    "hidden_act": "gelu",
    "hidden_size": 384,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 1536,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 77,
    "model_type": "metaclip_2_text_model",
    "num_attention_heads": 6,
    "num_hidden_layers": 12,
    "projection_dim": 384,
    "vocab_size": 901629
  },
  "transformers_version": "4.57.1",
  "vision_config": {
    "attention_dropout": 0.0,
    "dtype": "float32",
    "hidden_act": "gelu",
    "hidden_size": 384,
    "image_size": 224,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 1536,
    "layer_norm_eps": 1e-05,
    "model_type": "metaclip_2_vision_model",
    "num_attention_heads": 6,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "projection_dim": 384
  }
}