bilelomrani commited on
Commit
f9c95aa
β€’
1 Parent(s): 4d1741b

Upload tokenizer (#1)

Browse files

- Upload tokenizer (de68276dda6d94a0dc1b5875993ac1ddd898e9b5)

special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
+ "▁<PRE>",
8
+ "▁<MID>",
9
+ "▁<SUF>",
10
+ "▁<EOT>"
11
+ ],
12
+ "bos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "clean_up_tokenization_spaces": false,
21
+ "eos_token": {
22
+ "__type": "AddedToken",
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "eot_token": "▁<EOT>",
30
+ "fill_token": "<FILL_ME>",
31
+ "legacy": null,
32
+ "middle_token": "▁<MID>",
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": null,
35
+ "prefix_token": "▁<PRE>",
36
+ "sp_model_kwargs": {},
37
+ "suffix_token": "▁<SUF>",
38
+ "tokenizer_class": "CodeLlamaTokenizer",
39
+ "unk_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<unk>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "use_default_system_prompt": false
48
+ }