HachiML commited on
Commit
5f7af8e
1 Parent(s): 167b37b

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -1
tokenizer_config.json CHANGED
@@ -29,7 +29,7 @@
29
  },
30
  "additional_special_tokens": [],
31
  "bos_token": "<s>",
32
- "chat_template": "{% if messages[0]['role'] == 'system' %}\n{% set loop_messages = messages[1:] %}\n{% set system_message = messages[0]['content'] %}\n{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}\n{% set loop_messages = messages %}\n{% 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。' %}\n{% else %}\n{% set loop_messages = messages %}\n{% set system_message = false %}\n{% endif %}\n{{ bos_token }}\n{% for message in loop_messages %}\n{% if (message['role'] == 'user') != ((loop.index0 + (1 if messages[0]['role'] == 'assistant' else 0)) % 2 == 0) %}\n{{ raise_exception('Conversation roles must alternate starting from the first role.') }}\n{% endif %}\n{% if loop.index0 == 0 and system_message != false %}\n{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}\n{% else %}\n{% set content = message['content'] %}\n{% endif %}\n{% if message['role'] == 'user' %}\n{{ '[INST] ' + content.strip() + ' [/INST] ' }}\n{% elif message['role'] == 'system' %}\n{{ '<<SYS>>\n' + content.strip() + '\n<</SYS>>\n\n' }}\n{% elif message['role'] == 'assistant' %}\n{{ '' + content.strip() + '' + eos_token }}\n{% endif %}\n{% endfor %}\n",
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "</s>",
35
  "legacy": true,
 
29
  },
30
  "additional_special_tokens": [],
31
  "bos_token": "<s>",
32
+ "chat_template": "{% if messages[0]['role'] == 'system' %}\n{% set loop_messages = messages[1:] %}\n{% set system_message = messages[0]['content'] %}\n{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}\n{% set loop_messages = messages %}\n{% 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。' %}\n{% else %}\n{% set loop_messages = messages %}\n{% set system_message = false %}\n{% endif %}\n{% if not (messages[0]['role'] == 'assistant' and loop_messages|length > 0) %}\n{{ bos_token }}\n{% endif %}\n{% for message in loop_messages %}\n{% if (message['role'] == 'user') != ((loop.index0 + (1 if messages[0]['role'] == 'assistant' else 0)) % 2 == 0) %}\n{{ raise_exception('Conversation roles must alternate starting from the first role.') }}\n{% endif %}\n{% if loop.index0 == 0 and system_message != false %}\n{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}\n{% else %}\n{% set content = message['content'] %}\n{% endif %}\n{% if message['role'] == 'user' %}\n{{ '[INST] ' + content.strip() + ' [/INST] ' }}\n{% elif message['role'] == 'system' %}\n{{ '<<SYS>>\n' + content.strip() + '\n<</SYS>>\n\n' }}\n{% elif message['role'] == 'assistant' %}\n{{ '' + content.strip() + '' + eos_token }}\n{% endif %}\n{% endfor %}",
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "</s>",
35
  "legacy": true,