ztfmars
ztfmars
> > that's really a quick respond! thx very much!!! 1. i just wonder is it too heavy to use all layers to fuse together meanwhile add channel attention and...
hi~~ sorry to bother you again. here comes some new questions: (1) what's the version of your code's mmdetection? (2) i think the mmdetection's warm up ration is usually seted...
> thx for your answer and guide!
> 支持自定义视觉编码器么（llava-llama3）? 例如将clip换成siglip? 该如何实现？哪些代码需要修改？ 哇，兄弟，你也是看了google 的paligamma吗？sigclip这个确实要比vitclip好用啊。
> @ztfmars Thank you for your feedback > > 1. llava-llama3-70b We will support this in the near future, but for 120b we don't have that much computing power. >...
marked , look forward to the offical anwser!