chuonghoang commited on
Commit
0648f7f
1 Parent(s): 5d1f8e9

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +4 -0
tokenizer_config.json CHANGED
@@ -69,11 +69,15 @@
69
  "clean_up_tokenization_spaces": false,
70
  "eos_token": "</s>",
71
  "legacy": true,
 
72
  "model_max_length": 1000000000000000019884624838656,
73
  "pad_token": "</s>",
74
  "sp_model_kwargs": {},
75
  "spaces_between_special_tokens": false,
 
76
  "tokenizer_class": "LlamaTokenizer",
 
 
77
  "unk_token": "<unk>",
78
  "use_default_system_prompt": false,
79
  "use_fast": true
 
69
  "clean_up_tokenization_spaces": false,
70
  "eos_token": "</s>",
71
  "legacy": true,
72
+ "max_length": 1024,
73
  "model_max_length": 1000000000000000019884624838656,
74
  "pad_token": "</s>",
75
  "sp_model_kwargs": {},
76
  "spaces_between_special_tokens": false,
77
+ "stride": 0,
78
  "tokenizer_class": "LlamaTokenizer",
79
+ "truncation_side": "right",
80
+ "truncation_strategy": "longest_first",
81
  "unk_token": "<unk>",
82
  "use_default_system_prompt": false,
83
  "use_fast": true