Add chat_template to tokenizer_config.json
#23
by
irenedea
- opened
- tokenizer_config.json +2 -1
tokenizer_config.json
CHANGED
@@ -5,5 +5,6 @@
|
|
5 |
"eos_token": "<|endoftext|>",
|
6 |
"model_max_length": 8192,
|
7 |
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
-
"unk_token": "<|endoftext|>"
|
|
|
9 |
}
|
|
|
5 |
"eos_token": "<|endoftext|>",
|
6 |
"model_max_length": 8192,
|
7 |
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>",
|
9 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif not 'system' in messages[0]['role'] %}{% set loop_messages = messages %}{% set system_message = 'A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if system_message != false %}{{ '<|im_start|>system\n' + system_message.strip() + '\n'}}{% endif %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' }}{% else %}{{ '\n' + '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' }}{% endif %}{% if (add_generation_prompt == true) %}{{ '\n' + '<|im_start|>' + 'assistant' + '\n' }}{% elif (message['role'] == 'assistant') %}{% endif %}{% endfor %}"
|
10 |
}
|