{
  "architectures": [
    "BridgeTowerForContrastiveLearning"
  ],
  "contrastive_hidden_size": 512,
  "dtype": "float32",
  "hidden_act": "gelu",
  "hidden_size": 64,
  "init_layernorm_from_vision_encoder": false,
  "initializer_factor": 1,
  "intermediate_size": 128,
  "layer_norm_eps": 1e-05,
  "link_tower_type": "add",
  "logit_scale_init_value": 2.6592,
  "model_type": "bridgetower",
  "num_attention_heads": 4,
  "num_hidden_layers": 2,
  "share_cross_modal_transformer_layers": true,
  "share_link_tower_layers": false,
  "text_config": {
    "add_cross_attention": false,
    "attention_probs_dropout_prob": 0.1,
    "bos_token_id": 0,
    "eos_token_id": 2,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 64,
    "initializer_factor": 1e-10,
    "intermediate_size": 128,
    "is_decoder": false,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 514,
    "model_type": "bridgetower_text_model",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "pad_token_id": 1,
    "tie_word_embeddings": false,
    "type_vocab_size": 1,
    "use_cache": true,
    "vocab_size": 1025
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.15.0.dev0",
  "vision_config": {
    "batch_size": 1,
    "hidden_size": 64,
    "image_size": 64,
    "init_layernorm_from_vision_encoder": false,
    "initializer_factor": 1e-10,
    "is_training": false,
    "layer_norm_eps": 1e-05,
    "model_type": "bridgetower_vision_model",
    "num_channels": 3,
    "num_hidden_layers": 2,
    "num_image_features": 17,
    "patch_size": 16,
    "remove_last_layer": false,
    "share_layernorm": true,
    "stop_gradient": false
  }
}