Differences to 8b?
#2
by
dscarmo
- opened
Hello!
Could you clarify the differences between this weight and the 8B version?
The model cards suggest a Chat template while the original 8B version is a pure image text prompt.
Thank you for the great work in CheXagent.
The two models use different visual and textual backbone. You can check those configurations in their respective config.json files.
Chexagent-2-3b does in fact perform equally if not better than the 8b on some tasks. Chexagent-2-3b is also the model used and evaluated in our latest manuscript: https://arxiv.org/abs/2401.12208
IAMJB
changed discussion status to
closed