Add HF Chat template

#38
by anvdn - opened

I am trying to perform few-shot VQA with this model, however it's much more cumbersome than with Qwen2-VL because the tokenizer doesn't contain a chat template. Would it be possible to add one, so we can easily parse multi-turn conversations?
See:

Hey @anvdn , adding chat template for structured multi turn parsing is a great suggestion. We’ll pass this feedback to the team for consideration.
You can look at this: https://huggingface.co/allenai/Molmo-7B-D-0924/discussions/36

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

Sign up or log in to comment