Issues
- 45
Inquiry about downstream task evaluation
#9 opened by szrrr04 - 1
How to embed DCMHA into ViT
#12 opened by huangliqwe2020 - 0
Questions about training DCFormer
#8 opened by szrrr04 - 0
- 3
Something about training on Pile
#6 opened by szrrr04 - 18
a bug in the HLO->LLVM IR lowering
#5 opened by szrrr04 - 4
Cross Attention DCMHA
#4 opened by WhatMelonGua - 1
DCMHattention
#3 opened by Wangjinhong1998