{ "architectures": [ "OpenEndedVQAModel" ], "classifier_dropout": 0.3, "dropout": 0.5, "dtype": "float32", "gated_tanh": true, "hidden_size": 512, "image_feature_dim": 2048, "loss_type": "soft_ce", "mask_padding": true, "max_question_length": 15, "model_type": "open_ended_vqa", "num_answers": 3001, "num_regions": 36, "pad_token_id": 0, "pooling_dim": 16000, "transformers_version": "5.14.1", "use_cache": false, "vocab_size": 8597, "word_embed_dim": 512 }