{ "architectures": [ "VisualBertModel" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "bypass_transformer": false, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "initializer_range": 0.02, "intermediate_size": 37, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "visual_bert", "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 0, "special_visual_initialize": true, "torch_dtype": "float32", "transformers_version": "4.28.0.dev0", "type_vocab_size": 16, "visual_embedding_dim": 20, "vocab_size": 1124 }