vidyc commited on
Commit
6ffb254
·
verified ·
1 Parent(s): 97e795d

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +4 -0
tokenizer_config.json CHANGED
@@ -232,9 +232,13 @@
232
  "eos_token": "<|im_end|>",
233
  "errors": "replace",
234
  "extra_special_tokens": {},
 
235
  "model_max_length": 131072,
236
  "pad_token": "<|endoftext|>",
237
  "split_special_tokens": false,
 
238
  "tokenizer_class": "Qwen2Tokenizer",
 
 
239
  "unk_token": null
240
  }
 
232
  "eos_token": "<|im_end|>",
233
  "errors": "replace",
234
  "extra_special_tokens": {},
235
+ "max_length": 8192,
236
  "model_max_length": 131072,
237
  "pad_token": "<|endoftext|>",
238
  "split_special_tokens": false,
239
+ "stride": 0,
240
  "tokenizer_class": "Qwen2Tokenizer",
241
+ "truncation_side": "right",
242
+ "truncation_strategy": "longest_first",
243
  "unk_token": null
244
  }