config.json
| 1 | { |
| 2 | "_name_or_path": "../../saved_models/MichelBartels/tinyroberta-6l-768d-finetuned-step1/language_model.bin", |
| 3 | "architectures": [ |
| 4 | "RobertaForQuestionAnswering" |
| 5 | ], |
| 6 | "attention_probs_dropout_prob": 0.1, |
| 7 | "bos_token_id": 0, |
| 8 | "classifier_dropout": null, |
| 9 | "eos_token_id": 2, |
| 10 | "gradient_checkpointing": false, |
| 11 | "hidden_act": "gelu", |
| 12 | "hidden_dropout_prob": 0.1, |
| 13 | "hidden_size": 768, |
| 14 | "initializer_range": 0.02, |
| 15 | "intermediate_size": 3072, |
| 16 | "language": "english", |
| 17 | "layer_norm_eps": 1e-05, |
| 18 | "max_position_embeddings": 514, |
| 19 | "model_type": "roberta", |
| 20 | "name": "Roberta", |
| 21 | "num_attention_heads": 12, |
| 22 | "num_hidden_layers": 6, |
| 23 | "pad_token_id": 1, |
| 24 | "position_embedding_type": "absolute", |
| 25 | "torch_dtype": "float32", |
| 26 | "transformers_version": "4.7.0", |
| 27 | "type_vocab_size": 1, |
| 28 | "use_cache": true, |
| 29 | "vocab_size": 50265 |
| 30 | } |
| 31 | |