tokenizer_config.json
564 B · 25 lines · json Raw
1 {
2 "additional_special_tokens": null,
3 "bos_token": "<s>",
4 "cls_token": "<s>",
5 "eos_token": "</s>",
6 "mask_token": {
7 "__type": "AddedToken",
8 "content": "<mask>",
9 "lstrip": true,
10 "normalized": true,
11 "rstrip": false,
12 "single_word": false
13 },
14 "model_max_length": 1024,
15 "name_or_path": "facebook/nllb-200-distilled-600M",
16 "pad_token": "<pad>",
17 "sep_token": "</s>",
18 "sp_model_kwargs": {},
19 "special_tokens_map_file": null,
20 "src_lang": null,
21 "tgt_lang": null,
22 "tokenizer_class": "NllbTokenizer",
23 "unk_token": "<unk>"
24 }
25