qwen2-rloo-countdown-step150 / chat_template.jinja
thomasjhuang's picture
RLOO checkpoint at optimizer step 150 - Fixed prompt format, temp=0.1, lr=3e-6
8c36a57 verified
raw
history blame contribute delete
327 Bytes
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
You are a helpful assistant<|im_end|>
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
' + message['content'] + '<|im_end|>' + '
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
' }}{% endif %}