phdatdt commited on
Commit
0ec764a
1 Parent(s): 48e054c

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +7 -0
tokenizer_config.json CHANGED
@@ -930,9 +930,16 @@
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
 
933
  "model_max_length": 512,
 
934
  "pad_token": "<pad>",
 
 
935
  "sp_model_kwargs": {},
 
936
  "tokenizer_class": "T5Tokenizer",
 
 
937
  "unk_token": "<unk>"
938
  }
 
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
933
+ "max_length": 1024,
934
  "model_max_length": 512,
935
+ "pad_to_multiple_of": null,
936
  "pad_token": "<pad>",
937
+ "pad_token_type_id": 0,
938
+ "padding_side": "right",
939
  "sp_model_kwargs": {},
940
+ "stride": 0,
941
  "tokenizer_class": "T5Tokenizer",
942
+ "truncation_side": "right",
943
+ "truncation_strategy": "longest_first",
944
  "unk_token": "<unk>"
945
  }