lucidrains/memorizing-transformers-pytorch
Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch
PythonMIT
Issues
- 3
stable_softmax
#16 opened by huu4ontocord - 0
- 1
is it a t5 arch or decoder only gpt style arch?
#14 opened by brando90 - 0
hugging face training code with demo
#13 opened by brando90 - 1
official repo?
#12 opened by brando90 - 0
- 0
FAISS hard reset
#9 opened by itsdaniele - 0
index out of
#7 opened by chxiag - 0
Support for Multi-GPU training?
#6 opened by Victorwz - 8
- 1
- 3
Maybe scale is wrong
#3 opened by denadai2 - 79
Any interesting results?
#1 opened by rom1504