luffycodes commited on
Commit
6ae5347
1 Parent(s): cea1b36

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "</HAL>": 32000,
3
+ "</s>": 2,
4
+ "<HAL>": 32001,
5
+ "<s>": 1,
6
+ "<unk>": 0
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "</HAL>",
7
+ "<HAL>"
8
+ ],
9
+ "bos_token": "<s>",
10
+ "eos_token": "</s>",
11
+ "pad_token": "<unk>",
12
+ "unk_token": "<unk>"
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "</HAL>",
31
+ "lstrip": true,
32
+ "normalized": false,
33
+ "rstrip": true,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<HAL>",
39
+ "lstrip": true,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<unk>",
48
+ "<s>",
49
+ "</s>",
50
+ "</HAL>",
51
+ "<HAL>"
52
+ ],
53
+ "bos_token": "<s>",
54
+ "clean_up_tokenization_spaces": false,
55
+ "eos_token": "</s>",
56
+ "legacy": false,
57
+ "model_max_length": 4096,
58
+ "pad_token": "<unk>",
59
+ "padding_side": "right",
60
+ "sp_model_kwargs": {},
61
+ "spaces_between_special_tokens": false,
62
+ "tokenizer_class": "LlamaTokenizer",
63
+ "unk_token": "<unk>",
64
+ "use_default_system_prompt": true
65
+ }