ResearchTrend.AI
FlashNorm: fast normalization for LLMs

FlashNorm: fast normalization for LLMs

Nils Graef
Andrew Wasielewski
Matthew Clapp
ArXivPDFHTML

Papers citing "FlashNorm: fast normalization for LLMs"

2 / 2 papers shown
Title
Transformer tricks: Removing weights for skipless transformers
Transformer tricks: Removing weights for skipless transformers
Nils Graef
58
2
0
18 Apr 2024
RoFormer: Enhanced Transformer with Rotary Position Embedding
RoFormer: Enhanced Transformer with Rotary Position Embedding
Jianlin Su
Yu Lu
Shengfeng Pan
Ahmed Murtadha
Bo Wen
Yunfeng Liu
172
2,307
0
20 Apr 2021