Qingyu Chen
Results
3
comments of
Qingyu Chen
@RunningLeon 很感谢你的工作！想问下internvl-1.5的internlm2-20b 网络跟普通internlm2-20b有什么区别吗，我用了PR里的转换脚本转出来之后都是乱码。
> Which GPU? It should work with Hopper and Blackwell (B200). Ampere and Blackwell Geforce need a bit of fixing. b200
> Oh right varlen on B200 doesn't work yet (need some minor fix). You can use `flash_attn_func` KK, thanks for the reply, will stay tuned on this thread!