issues
search
microsoft
/
TransformerCompression
For releasing code related to compression methods for transformers, accompanying our publications
MIT License
354
stars
31
forks
source link
Add abstraction for QuarotFP16Linear layers in RTN quantization
#152
Closed
pashminacameron
closed
2 months ago
pashminacameron
commented
3 months ago
Added abstraction for module names. Needs testing
Added abstraction for module names. Needs testing