Transformer-Evolution-Paper

Ctrlk

README
数学符号
Act
Arch
FFN
Head
Memory
MHA
Normalize_And_Residual
Pe
Pretrain
Softmax
Others
LongConv
Rnn
CrossAttention
Inference
Peft
LLM

Powered by GitBook

On this page

MHA

FFT LocalGlobal MatrixMethod RightProduct SparseOrLowRank Others

PreviousAdapting Language Models to Compress Contexts NextFFT

Last updated 3 years ago