codelion commited on
Commit
a1e52c4
β€’
1 Parent(s): e07d3d4

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +30 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +52 -0
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": true,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": "</s>",
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
+ "▁<PRE>",
8
+ "▁<MID>",
9
+ "▁<SUF>",
10
+ "▁<EOT>",
11
+ "▁<PRE>",
12
+ "▁<MID>",
13
+ "▁<SUF>",
14
+ "▁<EOT>"
15
+ ],
16
+ "bos_token": {
17
+ "__type": "AddedToken",
18
+ "content": "<s>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "clean_up_tokenization_spaces": false,
25
+ "eos_token": {
26
+ "__type": "AddedToken",
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "eot_token": "▁<EOT>",
34
+ "fill_token": "<FILL_ME>",
35
+ "legacy": null,
36
+ "middle_token": "▁<MID>",
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": null,
39
+ "prefix_token": "▁<PRE>",
40
+ "sp_model_kwargs": {},
41
+ "suffix_token": "▁<SUF>",
42
+ "tokenizer_class": "CodeLlamaTokenizer",
43
+ "unk_token": {
44
+ "__type": "AddedToken",
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ },
51
+ "use_default_system_prompt": false
52
+ }