| { | |
| "MCQ_K": 256, | |
| "MCQ_M": 96, | |
| "_name_or_path": "/home/ukp/thakur/projects/JPQ/final_models/hotpotqa/gpl/epoch-1", | |
| "activation": "gelu", | |
| "architectures": [ | |
| "JPQTowerTASB" | |
| ], | |
| "attention_dropout": 0.1, | |
| "dim": 768, | |
| "dropout": 0.1, | |
| "gradient_checkpointing": true, | |
| "hidden_dim": 3072, | |
| "initializer_range": 0.02, | |
| "max_position_embeddings": 512, | |
| "model_type": "distilbert", | |
| "n_heads": 12, | |
| "n_layers": 6, | |
| "pad_token_id": 0, | |
| "qa_dropout": 0.1, | |
| "return_dict": false, | |
| "seq_classif_dropout": 0.2, | |
| "sinusoidal_pos_embds": false, | |
| "tie_weights_": true, | |
| "transformers_version": "4.3.3", | |
| "vocab_size": 30522 | |
| } | |