Hugging Face's logo

datajuicer
/
LLaMA-1B-dj-refine-150B

Text Generation
Transformers
PyTorch
19 datasets
llama
text-generation-inference
Inference Endpoints
Model card Files Community
zhijianma commited on
Commit
94d6559
•
1 Parent(s): bcb620c

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +7 -0
  2. special_tokens_map.json +36 -0
  3. tokenizer.json +0 -0
  4. tokenizer.model +3 -0
  5. tokenizer_config.json +87 -0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<CLS>": 32000,
3
+ "<EOD>": 32002,
4
+ "<MASK>": 32003,
5
+ "<PAD>": 32004,
6
+ "<SEP>": 32001
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<EOD>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": "<CLS>",
13
+ "eos_token": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "mask_token": "<MASK>",
21
+ "pad_token": {
22
+ "content": "<PAD>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "sep_token": "<SEP>",
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
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 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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": "<CLS>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<SEP>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<EOD>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<MASK>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<PAD>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ }
69
+ },
70
+ "additional_special_tokens": [
71
+ "<EOD>"
72
+ ],
73
+ "bos_token": "<s>",
74
+ "clean_up_tokenization_spaces": false,
75
+ "cls_token": "<CLS>",
76
+ "eos_token": "</s>",
77
+ "legacy": true,
78
+ "mask_token": "<MASK>",
79
+ "model_max_length": 2048,
80
+ "pad_token": "<PAD>",
81
+ "sep_token": "<SEP>",
82
+ "sp_model_kwargs": {},
83
+ "spaces_between_special_tokens": false,
84
+ "tokenizer_class": "LlamaTokenizer",
85
+ "unk_token": "<unk>",
86
+ "use_default_system_prompt": true
87
+ }