abhinavkulkarni commited on
Commit
b6f0632
β€’
1 Parent(s): a2f4ebf

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "▁<EOT>": 32003,
3
+ "▁<MID>": 32001,
4
+ "▁<PRE>": 32000,
5
+ "▁<SUF>": 32002
6
+ }
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "additional_special_tokens": [
5
+ "▁<PRE>",
6
+ "▁<MID>",
7
+ "▁<SUF>",
8
+ "▁<EOT>"
9
+ ],
10
+ "bos_token": {
11
+ "__type": "AddedToken",
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "clean_up_tokenization_spaces": false,
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "eot_token": "▁<EOT>",
28
+ "fill_token": "<FILL_ME>",
29
+ "legacy": null,
30
+ "middle_token": "▁<MID>",
31
+ "model_max_length": 1000000000000000019884624838656,
32
+ "pad_token": null,
33
+ "prefix_token": "▁<PRE>",
34
+ "sp_model_kwargs": {},
35
+ "suffix_first": false,
36
+ "suffix_token": "▁<SUF>",
37
+ "tokenizer_class": "CodeLlamaTokenizer",
38
+ "unk_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<unk>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ }
46
+ }