Gunulhona commited on
Commit
4436415
1 Parent(s): bc35e82

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +35 -5
  2. tokenizer.json +4 -2
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "mask_token": "<mask>",
5
- "pad_token": "<pad>",
6
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer.json CHANGED
@@ -2083,13 +2083,15 @@
2083
  "pre_tokenizer": {
2084
  "type": "Metaspace",
2085
  "replacement": "▁",
2086
- "add_prefix_space": true
 
2087
  },
2088
  "post_processor": null,
2089
  "decoder": {
2090
  "type": "Metaspace",
2091
  "replacement": "▁",
2092
- "add_prefix_space": true
 
2093
  },
2094
  "model": {
2095
  "type": "BPE",
 
2083
  "pre_tokenizer": {
2084
  "type": "Metaspace",
2085
  "replacement": "▁",
2086
+ "add_prefix_space": true,
2087
+ "prepend_scheme": "always"
2088
  },
2089
  "post_processor": null,
2090
  "decoder": {
2091
  "type": "Metaspace",
2092
  "replacement": "▁",
2093
+ "add_prefix_space": true,
2094
+ "prepend_scheme": "always"
2095
  },
2096
  "model": {
2097
  "type": "BPE",