arnabdhar commited on
Commit
a6fec2d
·
1 Parent(s): 9cfe820

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +7 -0
tokenizer_config.json CHANGED
@@ -46,12 +46,19 @@
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
 
49
  "model_max_length": 1000000000000000019884624838656,
50
  "never_split": null,
 
51
  "pad_token": "[PAD]",
 
 
52
  "sep_token": "[SEP]",
 
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",
 
 
56
  "unk_token": "[UNK]"
57
  }
 
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
+ "max_length": 512,
50
  "model_max_length": 1000000000000000019884624838656,
51
  "never_split": null,
52
+ "pad_to_multiple_of": null,
53
  "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
  "sep_token": "[SEP]",
57
+ "stride": 0,
58
  "strip_accents": null,
59
  "tokenize_chinese_chars": true,
60
  "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
  "unk_token": "[UNK]"
64
  }