tokenizer_config.json
567 B · 21 lines · json Raw
1 {
2 "bos_token": "<s>",
3 "cls_token": "<s>",
4 "eos_token": "</s>",
5 "mask_token": {
6 "__type": "AddedToken",
7 "content": "<mask>",
8 "lstrip": true,
9 "normalized": true,
10 "rstrip": false,
11 "single_word": false
12 },
13 "model_max_length": 512,
14 "name_or_path": "./results/mnli-xnli/mMiniLMv2-L12-H384-distilled-from-XLMR-Large-20220211/best-mMiniLMv2-L12-H384-distilled-from-XLMR-Large-20220211",
15 "pad_token": "<pad>",
16 "sep_token": "</s>",
17 "special_tokens_map_file": null,
18 "tokenizer_class": "XLMRobertaTokenizer",
19 "unk_token": "<unk>"
20 }
21