norabelrose commited on
Commit
84ef3e3
1 Parent(s): 4a7f6b7

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": "</s>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -31,11 +31,15 @@
31
  "clean_up_tokenization_spaces": false,
32
  "eos_token": "</s>",
33
  "legacy": false,
 
34
  "model_max_length": 1000000000000000019884624838656,
35
  "pad_token": "</s>",
36
  "padding_side": "right",
37
  "sp_model_kwargs": {},
 
38
  "tokenizer_class": "LlamaTokenizer",
 
 
39
  "unk_token": "<unk>",
40
  "use_default_system_prompt": false
41
  }
 
31
  "clean_up_tokenization_spaces": false,
32
  "eos_token": "</s>",
33
  "legacy": false,
34
+ "max_length": 1024,
35
  "model_max_length": 1000000000000000019884624838656,
36
  "pad_token": "</s>",
37
  "padding_side": "right",
38
  "sp_model_kwargs": {},
39
+ "stride": 0,
40
  "tokenizer_class": "LlamaTokenizer",
41
+ "truncation_side": "left",
42
+ "truncation_strategy": "longest_first",
43
  "unk_token": "<unk>",
44
  "use_default_system_prompt": false
45
  }