update the chat template
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -8005,7 +8005,7 @@
|
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
"bos_token": "<s>",
|
| 8008 |
-
"chat_template": "{%-
|
| 8009 |
"clean_up_tokenization_spaces": false,
|
| 8010 |
"eos_token": "</s>",
|
| 8011 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
"bos_token": "<s>",
|
| 8008 |
+
"chat_template": "{%- set language_pairs = {\"en-zh-cn\": {\"source\": \"English\", \"target\": \"Simplified Chinese\"}, \"en-zh\": {\"source\": \"English\", \"target\": \"Simplified Chinese\"}, \"en-zh-tw\": {\"source\": \"English\", \"target\": \"Traditional Chinese\"}, \"en-ar\": {\"source\": \"English\", \"target\": \"Arabic\"}, \"en-de\": {\"source\": \"English\", \"target\": \"German\"}, \"en-es-es\": {\"source\": \"English\", \"target\": \"European Spanish\"}, \"en-es-us\": {\"source\": \"English\", \"target\": \"Latin American Spanish\"}, \"en-fr\": {\"source\": \"English\", \"target\": \"French\"}, \"en-ja\": {\"source\": \"English\", \"target\": \"Japanese\"}, \"en-ko\": {\"source\": \"English\", \"target\": \"Korean\"}, \"en-ru\": {\"source\": \"English\", \"target\": \"Russian\"}, \"en-pt-br\": {\"source\": \"English\", \"target\": \"Brazilian Portuguese\"}} -%}\n{%- set system_message = '' -%}\n{%- set source_lang = '' -%}\n{%- set target_lang = '' -%}\n{%- if messages[0]['role'] == 'system' -%}\n {%- set lang_pair = messages[0]['content'] | trim -%}\n {%- set messages = messages[1:] -%}\n {%- if lang_pair in language_pairs -%}\n {%- set source_lang = language_pairs[lang_pair]['source'] -%}\n {%- set target_lang = language_pairs[lang_pair]['target'] -%}\n {%- set system_message = 'You are an expert at translating text from ' + source_lang + ' to ' + target_lang + '.' -%}\n {%- else -%}\n {%- set system_message = 'You are a translation expert.' -%}\n {%- endif -%}\n{%- endif -%}\n{{- '<s>System\\n' + system_message + '</s>\\n' -}}\n{%- for message in messages -%}\n {%- if (message['role'] in ['user']) != (loop.index0 % 2 == 0) -%}\n {{- raise_exception('Conversation roles must alternate between user and assistant') -}}\n {%- elif message['role'] == 'user' -%}\n {%- set user_content = (target_lang and 'What is the ' + target_lang + ' translation of the sentence: ' + message['content'] | trim or message['content'] | trim) -%}\n {{- '<s>User\\n' + user_content + '</s>\\n' -}}\n {%- elif message['role'] == 'assistant' -%}\n {{- '<s>Assistant\\n' + message['content'] | trim + '</s>\\n' -}}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{ '<s>Assistant\\n' }}\n{%- endif -%}",
|
| 8009 |
"clean_up_tokenization_spaces": false,
|
| 8010 |
"eos_token": "</s>",
|
| 8011 |
"model_max_length": 1000000000000000019884624838656,
|