config.json

{
    "drop_rate":0.1,
    "head_hidden_scale":2,
    "hidden_act":"gelu",
    "hidden_size":768,
    "image_size":288,
    "input_text_embed_size":768,
    "input_image_embed_size":768,
    "is_encoder_decoder":false,
    "layer_norm_eps":1e-5,
    "link_tower_shared":false,
    "link_tower_type":"add",
    "max_text_len":50,
    "mlp_ratio":4,
    "num_attention_heads":12,
    "num_hidden_layers":6,
    "stop_gradient":false,
    "tie_word_embeddings":false,
    "vocab_size":50265,
    "text_config_dict": null,
    "text_config":{
      "architectures": ["BridgeTowerTextModel"],
      "classifier_dropout": null,
      "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
    },
    "vision_config_dict": null,
    "vision_config":{
      "architectures": ["BridgeTowerVisionModel"],
      "embed_dim": 512,
      "input_resolution": 224,
      "width": 768,
      "layers": 12,
      "patch_size": 16,
      "transformer_width": 512,
      "output_resolution": 288,
      "stop_gradient": false,
      "vit_layernorm_shared": true,
      "vit_remove_last": false,
    }
}