Kye Gomez 289981ba01 [bugf][act-halting][gate halted positions from weight accumulation][bugf][moe-router-bias][stop ... load balance bias gradient leak][bugf][act-cache-consistency][keep all loops with kv cache][bugf][lora-depth-extrapolation][clamp scale index beyond max loops][improvement][pyproject-version][bump version to 0 4 0]		2026-04-20 09:17:43 -04:00
..
__init__.py	[docs][readme-badges][add pypi twitter github badges to	2026-04-19 23:18:05 -04:00
main.py	[bugf][act-halting][gate halted positions from weight accumulation][bugf][moe-router-bias][stop	2026-04-20 09:17:43 -04:00
moda.py	[docs][readme-badges][add pypi twitter github badges to	2026-04-19 23:18:05 -04:00
tokenizer.py	use gpt-oss tokenizer because it's a great tokenizer	2026-04-19 22:28:09 -04:00
variants.py	[Update variants with parameter count equation]	2026-04-19 21:55:06 -04:00