Results
2
issues of
Amy Lu
Great work on this project! I'm doing some benchmarking with key padding masking, but am getting a different answer for `xformers.components.attention.ScaledDotProduct` as compared to standard attention. Could you help clarify...
## Description Scripts for token selection by assessing per-token loss under a pretrained autoregressive model (ProtGPT2): * Distributed dataloading by pre-specifying the NumPy offsets in the FASTA loader * Load...