config.json
| 1 | { |
| 2 | "_name_or_path": "distilroberta-base", |
| 3 | "architectures": [ |
| 4 | "RobertaForMaskedLM" |
| 5 | ], |
| 6 | "attention_probs_dropout_prob": 0.1, |
| 7 | "bos_token_id": 0, |
| 8 | "eos_token_id": 2, |
| 9 | "gradient_checkpointing": false, |
| 10 | "hidden_act": "gelu", |
| 11 | "hidden_dropout_prob": 0.1, |
| 12 | "hidden_size": 768, |
| 13 | "initializer_range": 0.02, |
| 14 | "intermediate_size": 3072, |
| 15 | "layer_norm_eps": 1e-05, |
| 16 | "max_position_embeddings": 514, |
| 17 | "model_type": "roberta", |
| 18 | "num_attention_heads": 12, |
| 19 | "num_hidden_layers": 6, |
| 20 | "pad_token_id": 1, |
| 21 | "position_embedding_type": "absolute", |
| 22 | "transformers_version": "4.8.2", |
| 23 | "type_vocab_size": 1, |
| 24 | "use_cache": true, |
| 25 | "vocab_size": 50265 |
| 26 | } |
| 27 | |