kibrq commited on
Commit
8f70f91
·
1 Parent(s): d329cab

Update model

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "eos_token": "<s>",
3
+ "pad_token": "<pad>"
4
+ }
tokenizer.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 8,
8
+ "content": "<s>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 9,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ }
24
+ ],
25
+ "normalizer": null,
26
+ "pre_tokenizer": {
27
+ "type": "Sequence",
28
+ "pretokenizers": [
29
+ {
30
+ "type": "WhitespaceSplit"
31
+ }
32
+ ]
33
+ },
34
+ "post_processor": null,
35
+ "decoder": null,
36
+ "model": {
37
+ "type": "WordLevel",
38
+ "vocab": {
39
+ "-4": 0,
40
+ "-3": 1,
41
+ "-2": 2,
42
+ "-1": 3,
43
+ "1": 4,
44
+ "2": 5,
45
+ "3": 6,
46
+ "4": 7
47
+ },
48
+ "unk_token": "<unk>"
49
+ }
50
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "<s>",
3
+ "pad_token": "<pad>",
4
+ "tokenizer_class": "PreTrainedTokenizerFast"
5
+ }