yeontaek commited on
Commit
3aa9abe
1 Parent(s): b0867e0

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|PAD|>": 32001,
3
+ "<|end_of_turn|>": 32000
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|PAD|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": "<|end_of_turn|>",
14
+ "unk_token": {
15
+ "content": "<unk>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ }
21
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": true,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }