About downstream task apply?
#2
by
JackWang0601
- opened
Thank you for your excellent work! Could you explain how to apply Paligemma2 to downstream tasks such as object detection, Open-Vocal-Det, OCR, and others?
@JackWang0601 out of the box you can still do the tasks, e.g. "detect cat;dog" it's best if you fine-tune though. you can do so with this notebook https://github.com/merveenoyan/smol-vision/blob/main/Fine_tune_PaliGemma.ipynb