mrq 95da4e9405 made muon actually work by actually utilizing param groups (thanks APOLLO for reminding me this is the sane way to handle this split)		2025-02-26 10:39:13 -06:00
..
emb	borrowed muon since it might better work under deepspeed and not require cruft (even though it really does not like the masked-NAR, also make the masked-NAR faux-causal since it might better help out for cfg.model.version >= 7	2025-02-23 17:23:24 -06:00
engines	made muon actually work by actually utilizing param groups (thanks APOLLO for reminding me this is the sane way to handle this split)	2025-02-26 10:39:13 -06:00
models	made muon actually work by actually utilizing param groups (thanks APOLLO for reminding me this is the sane way to handle this split)	2025-02-26 10:39:13 -06:00
utils	made muon actually work by actually utilizing param groups (thanks APOLLO for reminding me this is the sane way to handle this split)	2025-02-26 10:39:13 -06:00
__init__.py
__main__.py
config.py	another experimental flag	2025-02-24 13:50:41 -06:00
data.py	ugh	2025-02-23 12:31:07 -06:00
demo.py
export.py
inference.py
metrics.py
plot.py
samplers.py
train.py	maybe fix NaNs being thrown for immature models at fp16 for training evals	2025-02-24 18:25:54 -06:00
webui.py