config.json

{
  "contrastive_hidden_size": 512,
  "share_cross_modal_transformer_layers": true,
  "drop_rate": 0.1,
  "head_hidden_scale": 2,
  "hidden_act": "gelu",
  "hidden_size": 1024,
  "initializer_factor": 1,
  "is_encoder_decoder": false,
  "layer_norm_eps": 1e-05,
  "share_link_tower_layers": false,
  "link_tower_type": "add",
  "num_attention_heads": 16,
  "num_hidden_layers": 6,
  "tie_word_embeddings": false,
  "text_config_dict": null,
  "init_layernorm_from_vision_encoder": false,
  "text_config": {
    "architectures": [
      "BridgeTowerTextModel"
    ],
    "vocab_size": 50265,
    "hidden_size": 1024,
    "num_hidden_layers": 24,
    "num_attention_heads": 16,
    "intermediate_size": 4096,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "attention_probs_dropout_prob": 0.1,
    "max_position_embeddings": 514,
    "type_vocab_size": 1,
    "initializer_factor": 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": 1024,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "image_size": 294,
    "initializer_factor": 1,
    "stop_gradient": false,
    "share_layernorm": true,
    "remove_last_layer": false
  }
}