Text Classification
Safetensors
xlm-roberta
antypasd commited on
Commit
0628a9f
1 Parent(s): aaad7f3

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -2
  2. tokenizer_config.json +5 -1
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
3
- size 17082756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
3
+ size 17082854
tokenizer_config.json CHANGED
@@ -46,9 +46,13 @@
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "mask_token": "<mask>",
49
- "model_max_length": 1000000000000000019884624838656,
 
50
  "pad_token": "<pad>",
51
  "sep_token": "</s>",
 
52
  "tokenizer_class": "XLMRobertaTokenizer",
 
 
53
  "unk_token": "<unk>"
54
  }
 
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "mask_token": "<mask>",
49
+ "max_length": 64,
50
+ "model_max_length": 512,
51
  "pad_token": "<pad>",
52
  "sep_token": "</s>",
53
+ "stride": 0,
54
  "tokenizer_class": "XLMRobertaTokenizer",
55
+ "truncation_side": "right",
56
+ "truncation_strategy": "longest_first",
57
  "unk_token": "<unk>"
58
  }