| { | |
| "architectures": [ | |
| "LxmertForQuestionAnswering" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 28, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 64, | |
| "l_layers": 2, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "lxmert", | |
| "num_attention_heads": 2, | |
| "num_attr_labels": 4, | |
| "num_hidden_layers": { | |
| "cross_encoder": 1, | |
| "language": 2, | |
| "vision": 1 | |
| }, | |
| "num_object_labels": 16, | |
| "num_qa_labels": 30, | |
| "pad_token_id": 0, | |
| "r_layers": 1, | |
| "task_mask_lm": true, | |
| "task_matched": true, | |
| "task_obj_predict": true, | |
| "task_qa": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.28.0.dev0", | |
| "type_vocab_size": 2, | |
| "visual_attr_loss": true, | |
| "visual_feat_dim": 128, | |
| "visual_feat_loss": true, | |
| "visual_loss_normalizer": 6.67, | |
| "visual_obj_loss": true, | |
| "visual_pos_dim": 4, | |
| "vocab_size": 1124, | |
| "x_layers": 1 | |
| } | |