config.json

{
    "share_cross_modal_transformer_layers": true,
    "drop_rate": 0.1,
    "head_hidden_scale": 2,
    "hidden_act": "gelu",
    "hidden_size": 768,
    "input_image_embed_size": 768,
    "input_text_embed_size": 768,
    "is_encoder_decoder": false,
    "layer_norm_eps": 1e-05,
    "share_link_tower_layers": false,
    "link_tower_type": "add",
    "max_text_len": 50,
    "mlp_ratio": 4,
    "num_attention_heads": 12,
    "num_hidden_layers": 6,
    "text_config_dict": null,
    "text_config":{
      "architectures": ["BridgeTowerTextModel"],
      "vocab_size": 50265,
      "hidden_size": 768,
      "num_hidden_layers": 12,
      "num_attention_heads": 12,
      "intermediate_size": 3072,
      "hidden_act": "gelu",
      "hidden_dropout_prob": 0.1,
      "attention_probs_dropout_prob": 0.1,
      "max_position_embeddings": 514,
      "type_vocab_size": 1,
      "initializer_range": 0.02,
      "layer_norm_eps": 1e-05,
      "pad_token_id": 1,
      "bos_token_id": 0,
      "eos_token_id": 2,
      "position_embedding_type": "absolute",
      "use_cache": true,
      "classifier_dropout": null
    },
    "vision_config_dict": null,
    "vision_config":{
      "architectures": ["BridgeTowerVisionModel"],
      "hidden_size": 768,
      "num_hidden_layers": 12,
      "patch_size": 16,
      "image_size": 288,
      "stop_gradient": false,
      "share_layernorm": true,
      "vit_remove_last": false,
      "init_layernorm_from_vit": false,
    }
}