| { |
| "architectures": [ |
| "BertForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "finetuning_task": "ours", |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "motivation", |
| "1": "background", |
| "2": "uses", |
| "3": "extends", |
| "4": "similarities", |
| "5": "differences", |
| "6": "future_work" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2, |
| "LABEL_3": 3, |
| "LABEL_4": 4, |
| "LABEL_5": 5, |
| "LABEL_6": 6 |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 0, |
| "type_vocab_size": 2, |
| "vocab_size": 31116 |
| } |
|
|
