lllyyyqqq

Results 6 issues of lllyyyqqq

![TW8U6CAT2~}RQARHC()KBOV](https://github.com/FlagOpen/FlagEmbedding/assets/48902561/d9c060dd-903d-473d-8b60-def9f53f087f) ![5@J@5}W8E%DH6A8ECKO)G7I](https://github.com/FlagOpen/FlagEmbedding/assets/48902561/a273bcbd-2183-4218-a83b-58715ef040e2) 发现有类似图中的差异,哪个更准呀?

请问flash attention 用的是v1吗,是什么版本啊

First, Excellent work! I am trying to reproduce using my own data, and change some of your code. During the training, at some steps, I got negative rl_loss, reg_loss, pg_loss,...

I am installing flash-attn in image, container environment as follow: ``` Ubuntu 16.04.6 pytorch image: nvcr.io/nvidia/pytorch: 22.04-py3 PyTorch Version 1.12.0a0+bd13bc6 CUDA 11.6 My card is V100-32g ``` Command `pip install...

I've seen the dkpd paper, the experiment results show dkpd works, but I don't really see why implement dpo to KD in the first place, and how it should improve...