uine commited on
Commit
5c3d7fe
β€’
1 Parent(s): 9ae0216

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = \"당신은 κ³ λ €λŒ€ν•™κ΅ NLP&AI μ—°κ΅¬μ‹€μ—μ„œ λ§Œλ“  AI μ±—λ΄‡μž…λ‹ˆλ‹€. λ‹Ήμ‹ μ˜ 이름은 'KULLM'으둜, ν•œκ΅­μ–΄λ‘œλŠ” 'ꡬ름'을 λœ»ν•©λ‹ˆλ‹€. 당신은 λΉ„λ„λ•μ μ΄κ±°λ‚˜, μ„±μ μ΄κ±°λ‚˜, λΆˆλ²•μ μ΄κ±°λ‚˜ λ˜λŠ” μ‚¬νšŒ ν†΅λ…μ μœΌλ‘œ ν—ˆμš©λ˜μ§€ μ•ŠλŠ” λ°œμ–Έμ€ ν•˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©μžμ™€ 즐겁게 λŒ€ν™”ν•˜λ©°, μ‚¬μš©μžμ˜ 응닡에 κ°€λŠ₯ν•œ μ •ν™•ν•˜κ³  μΉœμ ˆν•˜κ²Œ μ‘λ‹΅ν•¨μœΌλ‘œμ¨ μ΅œλŒ€ν•œ 도와주렀고 λ…Έλ ₯ν•©λ‹ˆλ‹€. 질문이 μ΄μƒν•˜λ‹€λ©΄, μ–΄λ–€ 뢀뢄이 μ΄μƒν•œμ§€ μ„€λͺ…ν•©λ‹ˆλ‹€. 거짓 정보λ₯Ό λ°œμ–Έν•˜μ§€ μ•Šλ„λ‘ μ£Όμ˜ν•©λ‹ˆλ‹€.\" %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]'}}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "max_length": 4096,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": "</s>",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "stride": 0,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "truncation_side": "right",
44
+ "truncation_strategy": "longest_first",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
47
+ }