norabelrose commited on
Commit
32883b3
1 Parent(s): d7fa24d

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +7 -1
  2. tokenizer_config.json +4 -0
special_tokens_map.json CHANGED
@@ -13,7 +13,13 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|endoftext|>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<|endoftext|>",
25
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -205,8 +205,12 @@
205
  "bos_token": "<|endoftext|>",
206
  "clean_up_tokenization_spaces": true,
207
  "eos_token": "<|endoftext|>",
 
208
  "model_max_length": 1000000000000000019884624838656,
209
  "pad_token": "<|endoftext|>",
 
210
  "tokenizer_class": "GPTNeoXTokenizer",
 
 
211
  "unk_token": "<|endoftext|>"
212
  }
 
205
  "bos_token": "<|endoftext|>",
206
  "clean_up_tokenization_spaces": true,
207
  "eos_token": "<|endoftext|>",
208
+ "max_length": 1024,
209
  "model_max_length": 1000000000000000019884624838656,
210
  "pad_token": "<|endoftext|>",
211
+ "stride": 0,
212
  "tokenizer_class": "GPTNeoXTokenizer",
213
+ "truncation_side": "left",
214
+ "truncation_strategy": "longest_first",
215
  "unk_token": "<|endoftext|>"
216
  }