andreaskoepf commited on
Commit
ac7f5bb
1 Parent(s): 84f7a46

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<CLS>": 32000,
3
+ "<EOD>": 32002,
4
+ "<MASK>": 32003,
5
+ "<PAD>": 32004,
6
+ "<SEP>": 32001,
7
+ "<|im_end|>": 32006,
8
+ "<|im_start|>": 32005
9
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": "<|im_start|>",
7
+ "cls_token": "<CLS>",
8
+ "eos_token": "<|im_end|>",
9
+ "mask_token": "<MASK>",
10
+ "pad_token": "<PAD>",
11
+ "sep_token": "<SEP>",
12
+ "unk_token": {
13
+ "content": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ }
19
+ }
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
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": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }