GG2k4 commited on
Commit
bdabc7a
·
verified ·
1 Parent(s): bee2db7

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +7 -1
  2. tokenizer.json +2 -11
special_tokens_map.json CHANGED
@@ -13,7 +13,13 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|endoftext|>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<|endoftext|>",
25
  "lstrip": false,
tokenizer.json CHANGED
@@ -2,20 +2,11 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 1000,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 1000
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 50256,
16
- "pad_type_id": 0,
17
- "pad_token": "<|endoftext|>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 50256,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 150,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
+ "padding": null,
 
 
 
 
 
 
 
 
 
10
  "added_tokens": [
11
  {
12
  "id": 50256,