Spaces:

ProCreations
/

repro-nanoquant-efficient-sub-1-bit-quantization-of-large-language-models

Running

repro-nanoquant-efficient-sub-1-bit-quantization-of-large-language-models / code

5.37 kB

Ctrl+K

1 contributor

Add the missing Claim 5 page: rerun the COMPAS case study on real ProPublica data; optimal fair thresholds differ by 0.08-0.13 across groups and forcing a single threshold costs 52-341 utility

0690c42 verified 5 days ago

compas_exp.py

5.37 kB
Add the missing Claim 5 page: rerun the COMPAS case study on real ProPublica data; optimal fair thresholds differ by 0.08-0.13 across groups and forcing a single threshold costs 52-341 utility 5 days ago