config.json
| 1 | { |
| 2 | "_name_or_path": "./results/mnli-xnli/mMiniLMv2-L12-H384-distilled-from-XLMR-Large-20220211/best-mMiniLMv2-L12-H384-distilled-from-XLMR-Large-20220211", |
| 3 | "architectures": [ |
| 4 | "XLMRobertaForSequenceClassification" |
| 5 | ], |
| 6 | "attention_probs_dropout_prob": 0.1, |
| 7 | "bos_token_id": 0, |
| 8 | "classifier_dropout": null, |
| 9 | "eos_token_id": 2, |
| 10 | "hidden_act": "gelu", |
| 11 | "hidden_dropout_prob": 0.1, |
| 12 | "hidden_size": 384, |
| 13 | "id2label": { |
| 14 | "0": "entailment", |
| 15 | "1": "neutral", |
| 16 | "2": "contradiction" |
| 17 | }, |
| 18 | "initializer_range": 0.02, |
| 19 | "intermediate_size": 1536, |
| 20 | "label2id": { |
| 21 | "contradiction": 2, |
| 22 | "entailment": 0, |
| 23 | "neutral": 1 |
| 24 | }, |
| 25 | "layer_norm_eps": 1e-05, |
| 26 | "max_position_embeddings": 514, |
| 27 | "model_type": "xlm-roberta", |
| 28 | "num_attention_heads": 12, |
| 29 | "num_hidden_layers": 12, |
| 30 | "pad_token_id": 1, |
| 31 | "position_embedding_type": "absolute", |
| 32 | "problem_type": "single_label_classification", |
| 33 | "torch_dtype": "float32", |
| 34 | "transformers_version": "4.26.0", |
| 35 | "type_vocab_size": 1, |
| 36 | "use_cache": true, |
| 37 | "vocab_size": 250002 |
| 38 | } |
| 39 | |