Taishi-N324
commited on
Commit
•
5b6bde2
1
Parent(s):
35224cb
Upload tokenizer_config.json
Browse files- tokenizer_config.json +26 -35
tokenizer_config.json
CHANGED
@@ -1,45 +1,36 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"
|
5 |
-
|
6 |
-
"
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
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 |
},
|
31 |
-
"
|
32 |
-
"bos_token": "<s>",
|
33 |
-
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['text'] %}{% elif false == true and not '<<SYS>>' in messages[0]['text'] %}{% set loop_messages = messages %}{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{{ bos_token }}{% 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['text'] %}{% else %}{% set content = message['text'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[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 %}",
|
34 |
"clean_up_tokenization_spaces": false,
|
35 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
"legacy": false,
|
37 |
"model_max_length": 1000000000000000019884624838656,
|
38 |
-
"pad_token":
|
39 |
"padding_side": "right",
|
40 |
"sp_model_kwargs": {},
|
41 |
-
"spaces_between_special_tokens": false,
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
43 |
-
"unk_token":
|
44 |
-
|
45 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
},
|
12 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{{ bos_token }}{% 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' %}{{ '[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 %}",
|
|
|
|
|
13 |
"clean_up_tokenization_spaces": false,
|
14 |
+
"eos_token": {
|
15 |
+
"__type": "AddedToken",
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
"legacy": false,
|
23 |
"model_max_length": 1000000000000000019884624838656,
|
24 |
+
"pad_token": null,
|
25 |
"padding_side": "right",
|
26 |
"sp_model_kwargs": {},
|
|
|
27 |
"tokenizer_class": "LlamaTokenizer",
|
28 |
+
"unk_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
}
|
36 |
+
}
|