Taishi-N324 commited on
Commit
c57de3a
1 Parent(s): 67d8ea0

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +5 -5
tokenizer_config.json CHANGED
@@ -5,17 +5,17 @@
5
  "__type": "AddedToken",
6
  "content": "<s>",
7
  "lstrip": false,
8
- "normalized": true,
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]['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 %}",
13
  "clean_up_tokenization_spaces": false,
14
  "eos_token": {
15
  "__type": "AddedToken",
16
  "content": "</s>",
17
  "lstrip": false,
18
- "normalized": true,
19
  "rstrip": false,
20
  "single_word": false
21
  },
@@ -29,8 +29,8 @@
29
  "__type": "AddedToken",
30
  "content": "<unk>",
31
  "lstrip": false,
32
- "normalized": true,
33
  "rstrip": false,
34
  "single_word": false
35
  }
36
- }
 
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
  },
 
29
  "__type": "AddedToken",
30
  "content": "<unk>",
31
  "lstrip": false,
32
+ "normalized": false,
33
  "rstrip": false,
34
  "single_word": false
35
  }
36
+ }