Why is there a chat template for a base model?
#11
by
dsouzaJithesh
- opened
As far as I am aware, apply_chat_template and the special chat tokens are for instruction models. But this model contains these funcs. Why is that ? I am aiming to fine this model. Should this change how I approach SFT?
I am new to this. Any help will be greatly appreciated.
I got the answer. Terminology for qwen is different. If the model name has no suffix it is the instruct model. The base model has suffix -base.