imdatta0 commited on
Commit
d25b1fc
1 Parent(s): 557fd0b

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +42 -1
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,5 +1,46 @@
1
  {
2
- "added_tokens_decoder": {},
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "clean_up_tokenization_spaces": false,
4
  "model_max_length": 1000000000000000019884624838656,
5
  "tokenizer_class": "PreTrainedTokenizerFast"
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|pad|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|bos|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|unk|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<|mask|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
  "clean_up_tokenization_spaces": false,
45
  "model_max_length": 1000000000000000019884624838656,
46
  "tokenizer_class": "PreTrainedTokenizerFast"