mrq 70cf694cfd output attention scores for SDPA/flash, since naive attention seems broken		2024-10-12 12:09:17 -05:00
..
arch	output attention scores for SDPA/flash, since naive attention seems broken	2024-10-12 12:09:17 -05:00
__init__.py
ar_nar.py	modified demo page to be more modular with demoing comparisons, actually provide a path to use modified naive attention, entropix sampling is not tied to an experimental yaml flag now	2024-10-12 11:27:55 -05:00
ar.py	added min-p (really does not seem useful since it's very sensitive), more tweaks to entropix	2024-10-11 22:36:06 -05:00
base.py	modified demo page to be more modular with demoing comparisons, actually provide a path to use modified naive attention, entropix sampling is not tied to an experimental yaml flag now	2024-10-12 11:27:55 -05:00
experimental.py
lora.py
nar.py	added min-p (really does not seem useful since it's very sensitive), more tweaks to entropix	2024-10-11 22:36:06 -05:00