mrq 7d2e64630c lol		2025-02-26 10:49:06 -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	lol	2025-02-26 10:49:06 -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	added option to playback audio directly, removed no-phonemize option since I swear it worked in testing but it doesn't actually work	2025-01-12 21:52:49 -06:00
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	sanity checks (and I realized that the model actually had langs set to 4 in the yaml for KO/ZH so................	2024-12-19 19:08:57 -06:00
export.py		2024-12-26 21:42:17 -06:00
inference.py	added muon optimizer through kludge hacks because it necessitates a second optimizer in tandum that seems to only sometimes work with deepspeed	2025-02-23 11:22:13 -06:00
metrics.py
plot.py
samplers.py	agony	2025-02-12 00:18:24 -06:00
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	added option to playback audio directly, removed no-phonemize option since I swear it worked in testing but it doesn't actually work	2025-01-12 21:52:49 -06:00