aframson commited on
Commit
70fa35a
·
1 Parent(s): b8b2c14
Files changed (1) hide show
  1. tokenizer_config.json +17 -34
tokenizer_config.json CHANGED
@@ -1,36 +1,19 @@
1
  {
2
- "auto_map": {
3
- "AutoTokenizer": ["tokenizeConfig.OBITokenizer", null]
4
- },
5
- "add_bos_token": false,
6
- "add_eos_token": false,
7
- "use_fast": false,
8
- "clean_up_tokenization_spaces": false,
9
- "eos_token": {
10
- "__type": "AddedToken",
11
- "content": "</s>",
12
- "lstrip": false,
13
- "normalized": true,
14
- "rstrip": false,
15
- "single_word": true
16
- },
17
- "model_max_length": 4096,
18
- "sp_model_kwargs": {},
19
- "tokenizer_class": "OBITokenizer",
20
- "pad_token": {
21
- "__type": "AddedToken",
22
- "content": "<unk>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": true
27
- },
28
- "unk_token": {
29
- "__type": "AddedToken",
30
- "content": "<unk>",
31
- "lstrip": false,
32
- "normalized": true,
33
- "rstrip": false,
34
- "single_word": true
35
- }
36
  }
 
 
 
 
1
  {
2
+ "auto_map": {
3
+ "AutoTokenizer": ["tokenizeConfig.OBITokenizer", null]
4
+ },
5
+ "add_prefix_space": false,
6
+ "additional_special_tokens": [
7
+ "</s>",
8
+ "<s>",
9
+ "<unk>"
10
+ ],
11
+ "bos_token": "<s>",
12
+ "eos_token": "</s>",
13
+ "tokenizer_class": "OBITokenizer",
14
+ "unk_token": "</s>",
15
+ "vocab_size": 10187
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  }
17
+
18
+
19
+