-
https://blog.gangxing.moe/favourites/
I am little Gangxing.
-
https://blog.iacg.moe/2016/11/30/%E5%A6%82%E4%BD%95%E5%9C%A8Coding%E4%B8%8A%E9%83%A8%E7%BD%B2Hexo/
Hexo Theme Keep
-
### Source name
Sukebei.Nyaa
### Source link
https://sukebei.nyaa.si/
### Language
Japanese, English
### Source type
Anime
### Additional info
I'm talking about Hentai.
I hope these sites wi…
-
您好,我是[Experts Weights Averaging: A New General Training Scheme for Vision Transformers](https://arxiv.org/abs/2308.06093)的作者,在看完您的这篇文章后,我发现您文章中提出的SS-MoE与我的EWA框架完全一致,但我并没有在文章中看到对EWA的引用。
-
http://blog.gangxing.moe/tags/
I am little Gangxing.
-
https://blog.gangxing.moe/leetcode1684/
I am little Gangxing.
-
Hello everyone.
When I trained Mixtral-MOE with QLoRA + Zero3, it occurs error like below.
…
-
Moe misidentifies tracks from different albums as as being the same track.
https://i.imgur.com/TXJ6Qtr.png
![image](https://user-images.githubusercontent.com/122204859/223669886-42f1a1b3-f67d-43…
-
I don't have any idea to create dataset for LGM models.
-
Hello! first off thanks for the hard work!
is there plans to add Command R and R+ support?
I am attempting too but im a little out of my depth.
Thanks again!