ohmreborn commited on
Commit
0449d38
1 Parent(s): edd93fc

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<bot>:": 256009,
3
+ "<human>:": 256008
4
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c49dc7e82c10227af764e518924cf2f9d50c00462750d184fa74697bba65eef8
3
+ size 4920706
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<madeupword0>",
4
+ "<madeupword1>",
5
+ "<madeupword2>",
6
+ "<madeupword3>",
7
+ "<madeupword4>",
8
+ "<madeupword5>",
9
+ "<madeupword6>"
10
+ ],
11
+ "bos_token": "<s>",
12
+ "cls_token": "<s>",
13
+ "eos_token": "</s>",
14
+ "pad_token": "<pad>",
15
+ "sep_token": "</s>",
16
+ "unk_token": "<unk>"
17
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<madeupword0>",
4
+ "<madeupword1>",
5
+ "<madeupword2>",
6
+ "<madeupword3>",
7
+ "<madeupword4>",
8
+ "<madeupword5>",
9
+ "<madeupword6>"
10
+ ],
11
+ "bos_token": "<s>",
12
+ "clean_up_tokenization_spaces": true,
13
+ "cls_token": "<s>",
14
+ "eos_token": "</s>",
15
+ "model_max_length": 2048,
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "XGLMTokenizer",
20
+ "tokenizer_file": null,
21
+ "unk_token": "<unk>"
22
+ }