bjoernp commited on
Commit
f8e7c01
1 Parent(s): a72ea38

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0,
5
+ "<|im_end|>": 32001,
6
+ "<|im_start|>": 32000
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "<|im_start|>",
7
+ "<|im_end|>"
8
+ ],
9
+ "bos_token": "<s>",
10
+ "eos_token": "</s>",
11
+ "unk_token": "<unk>"
12
+ }
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 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": true,
32
+ "normalized": false,
33
+ "rstrip": true,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_end|>",
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
+ "<|im_start|>",
51
+ "<|im_end|>"
52
+ ],
53
+ "bos_token": "<s>",
54
+ "clean_up_tokenization_spaces": false,
55
+ "eos_token": "</s>",
56
+ "legacy": false,
57
+ "model_max_length": 1000000000000000019884624838656,
58
+ "pad_token": null,
59
+ "padding_side": "right",
60
+ "sp_model_kwargs": {},
61
+ "spaces_between_special_tokens": false,
62
+ "tokenizer_class": "LlamaTokenizer",
63
+ "tokenizer_file": "/pfss/mlde/workspaces/mlde_wsp_Laion/huggingface/hub/models--bjoernp--leo-big/snapshots/0f9d0d2f9a16099cda0b3c25c175679c9628cdb1/tokenizer.json",
64
+ "unk_token": "<unk>",
65
+ "use_default_system_prompt": true
66
+ }