nilabhra epignatelli commited on
Commit
0b9684d
1 Parent(s): cf4b3c4

add chat template to tokenizer_config.json (#111)

Browse files

- add chat template to tokenizer_config.json (16962019561b0f0c8ae490f1fb3fc4a3f8272778)


Co-authored-by: Eduardo Pignatelli <[email protected]>

Files changed (1) hide show
  1. tokenizer_config.json +2 -1
tokenizer_config.json CHANGED
@@ -8,5 +8,6 @@
8
  "model_max_length": 2048,
9
  "name_or_path": "tiiuae/falcon_tokenizer",
10
  "special_tokens_map_file": null,
11
- "tokenizer_class": "PreTrainedTokenizerFast"
 
12
  }
 
8
  "model_max_length": 2048,
9
  "name_or_path": "tiiuae/falcon_tokenizer",
10
  "special_tokens_map_file": null,
11
+ "tokenizer_class": "PreTrainedTokenizerFast",
12
+ "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 = '' %}{% 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 %}{{ system_message.strip() }}{% endif %}{% if message['role'] == 'user' %}{{ '\n\nUser: ' + message['content'].strip().replace('\r\n', '\n').replace('\n\n', '\n') }}{% elif message['role'] == 'assistant' %}{{ '\n\nAssistant: ' + message['content'].strip().replace('\r\n', '\n').replace('\n\n', '\n') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\nAssistant:' }}{% endif %}"
13
  }