Hugging Face's logo

Adun
/
openthaigpt-1.0.0-7b-chat-pantip

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
Model card Files Community
Adun commited on
Commit
73577a2
•
1 Parent(s): 4a76e31

Upload 5 files

Browse files
Files changed (5) hide show
  1. added_tokens.json +23 -0
  2. special_tokens_map.json +14 -0
  3. tokenizer.json +0 -0
  4. tokenizer.model +3 -0
  5. tokenizer_config.json +86 -0
added_tokens.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<CLS>": 41070,
4
+ "<EOD>": 41072,
5
+ "<MASK>": 41073,
6
+ "<PAD>": 41074,
7
+ "<SEP>": 41071,
8
+ "<s>": 1,
9
+ "<unk>": 0,
10
+ "<unused1>":41075,
11
+ "<unused2>":41076,
12
+ "<unused3>":41077,
13
+ "<unused4>":41078,
14
+ "<unused5>":41079,
15
+ "<unused6>":41080,
16
+ "<unused7>":41081,
17
+ "<unused8>":41082,
18
+ "<unused9>":41083,
19
+ "<unused10>":41084,
20
+ "<unused11>":41085,
21
+ "<unused12>":41086,
22
+ "<unused13>":41087
23
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<CLS>",
9
+ "eos_token": "</s>",
10
+ "mask_token": "<MASK>",
11
+ "pad_token": "<PAD>",
12
+ "sep_token": "<SEP>",
13
+ "unk_token": "<unk>"
14
+ }
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 sha256:02df43dcae8c7b5b122d45f642e42c96577cdd09fd949c6996051886c72ab002
3
+ size 717508
tokenizer_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "41070": {
30
+ "content": "<CLS>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "41071": {
38
+ "content": "<SEP>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "41072": {
46
+ "content": "<EOD>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "41073": {
54
+ "content": "<MASK>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "41074": {
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
+ "<unk>",
72
+ "<s>",
73
+ "</s>"
74
+ ],
75
+ "bos_token": "<s>",
76
+ "clean_up_tokenization_spaces": false,
77
+ "eos_token": "</s>",
78
+ "legacy": true,
79
+ "model_max_length": 1000000000000000019884624838656,
80
+ "pad_token": "<PAD>",
81
+ "sp_model_kwargs": {},
82
+ "spaces_between_special_tokens": false,
83
+ "tokenizer_class": "LlamaTokenizer",
84
+ "unk_token": "<unk>",
85
+ "use_default_system_prompt": true
86
+ }