IAMRS23 commited on
Commit
02b9f34
·
verified ·
1 Parent(s): cd96781

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -2
  2. tokenizer_config.json +7 -0
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 146,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 146
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 71,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 71
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
tokenizer_config.json CHANGED
@@ -109,8 +109,15 @@
109
  "errors": "replace",
110
  "extra_special_tokens": {},
111
  "full_tokenizer_file": null,
 
112
  "model_max_length": 1000000000000000019884624838656,
 
113
  "pad_token": "<|endoftext|>",
 
 
 
114
  "tokenizer_class": "GPT2Tokenizer",
 
 
115
  "unk_token": "<|endoftext|>"
116
  }
 
109
  "errors": "replace",
110
  "extra_special_tokens": {},
111
  "full_tokenizer_file": null,
112
+ "max_length": 146,
113
  "model_max_length": 1000000000000000019884624838656,
114
+ "pad_to_multiple_of": null,
115
  "pad_token": "<|endoftext|>",
116
+ "pad_token_type_id": 0,
117
+ "padding_side": "right",
118
+ "stride": 0,
119
  "tokenizer_class": "GPT2Tokenizer",
120
+ "truncation_side": "right",
121
+ "truncation_strategy": "longest_first",
122
  "unk_token": "<|endoftext|>"
123
  }