TimeRobber commited on
Commit
d2c9f5c
1 Parent(s): 763a939

Add fast tokenizer (#1)

Browse files

- Add fast tokenizer (5ef4bc8c9d710101e397a5e588e4dcb68b8b3edd)

Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +30 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +41 -0
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "</s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "name_or_path": "facebook/opt-125m",
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<pad>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "special_tokens_map_file": null,
32
+ "tokenizer_class": "GPT2Tokenizer",
33
+ "unk_token": {
34
+ "__type": "AddedToken",
35
+ "content": "</s>",
36
+ "lstrip": false,
37
+ "normalized": true,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff