Fawass commited on
Commit
bee4aff
·
verified ·
1 Parent(s): 5fa52dc

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<CLS>": 41070,
3
+ "<EOD>": 41072,
4
+ "<MASK>": 41073,
5
+ "<PAD>": 41074,
6
+ "<SEP>": 41071
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<PAD>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
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 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "41070": {
31
+ "content": "<CLS>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "41071": {
39
+ "content": "<SEP>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "41072": {
47
+ "content": "<EOD>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "41073": {
55
+ "content": "<MASK>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "41074": {
63
+ "content": "<PAD>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ }
70
+ },
71
+ "additional_special_tokens": [
72
+ "<unk>",
73
+ "<s>",
74
+ "</s>"
75
+ ],
76
+ "bos_token": "<s>",
77
+ "chat_template": "{{ bos_token }}{{ 'คุณเป็น AI ที่เชี่ยวชาญเฉพาะเรื่อง AiBeacon และสามารถเข้าใจคำถามได้ทั้งภาษาไทยและภาษาอังกฤษ\nหากมีคำถามนอกเหนือจากข้อมูล AiBeacon ให้ตอบว่า \"ขออภัย ฉันตอบได้เฉพาะคำถามเกี่ยวกับ AiBeacon เท่านั้น\"\n\nYou are an AI specialized in AiBeacon and can understand questions in both Thai and English.\nFor questions outside of AiBeacon information, respond with \"Sorry, I can only answer questions about AiBeacon.\"' }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n\n### คำถาม/Question:\n' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ '\n\n### คำตอบ/Answer:\n' + message['content'] + '</s>' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\n### คำตอบ/Answer:\n' }}{% endif %}",
78
+ "clean_up_tokenization_spaces": false,
79
+ "eos_token": "</s>",
80
+ "legacy": false,
81
+ "model_max_length": 4096,
82
+ "pad_token": "<PAD>",
83
+ "padding_side": "left",
84
+ "sp_model_kwargs": {},
85
+ "spaces_between_special_tokens": false,
86
+ "tokenizer_class": "LlamaTokenizer",
87
+ "unk_token": "<unk>",
88
+ "use_default_system_prompt": true
89
+ }