Open lucasjinreal opened 5 months ago
Hi, I adopt this Resampler module to LLaVa without slicing, and replace the vision encoder from CLIP to siglip, the loss can not converge.
Any thought about this?
Hi, I adopt this Resampler module to LLaVa without slicing, and replace the vision encoder from CLIP to siglip, the loss can not converge.
Any thought about this?