Chat template clarification

#1
by mtglearn - opened

The readme says “ They can be prompted in the same way as Prometheus-2” but the Prometheus-2 readme specifies to use the mistral chat template.

Should we use the Qwen chat template with this model or was this trained on the mistral template?

Thanks!

Unbabel org

Hey, yes, you should use Qwen's chat template (e.g., through the tokenizer's apply_chat_template function).
What I meant is that the model's prompt (i.e., what is inside the chat template) is the same as Prometheus 2.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment