michaelfeil commited on
Commit
e0c812c
1 Parent(s): 8825f3f

Add a goddamn max length parameter to your tokenizer.

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +2 -2
tokenizer_config.json CHANGED
@@ -46,10 +46,10 @@
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
  "sp_model_kwargs": {},
53
  "tokenizer_class": "XLMRobertaTokenizer",
54
- "unk_token": "<unk>"
55
  }
 
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
  "pad_token": "<pad>",
51
  "sep_token": "</s>",
52
  "sp_model_kwargs": {},
53
  "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>",
55
  }