julian-schelb commited on
Commit
818382f
1 Parent(s): 49b1c97

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +11 -5
tokenizer_config.json CHANGED
@@ -3,13 +3,19 @@
3
  "bos_token": "<s>",
4
  "cls_token": "<s>",
5
  "eos_token": "</s>",
6
- "errors": "replace",
7
- "mask_token": "<mask>",
8
- "name_or_path": "xlm-roberta-large",
 
 
 
 
 
 
 
9
  "pad_token": "<pad>",
10
  "sep_token": "</s>",
11
  "special_tokens_map_file": null,
12
- "tokenizer_class": "RobertaTokenizer",
13
- "trim_offsets": true,
14
  "unk_token": "<unk>"
15
  }
 
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": 512,
15
+ "name_or_path": "./results/checkpoint-final-20-langs/",
16
  "pad_token": "<pad>",
17
  "sep_token": "</s>",
18
  "special_tokens_map_file": null,
19
+ "tokenizer_class": "XLMRobertaTokenizer",
 
20
  "unk_token": "<unk>"
21
  }