mrq 77ff23e319 repeat extend the prom to fill the initial tokens for nar-len (it somewhat works, the model just needs to train more)		2024-11-06 23:29:53 -06:00
..
emb	ugh	2024-11-05 11:50:05 -06:00
engines	Windows specific fixes (to-do: find libespeak-ng.dll automatically because it cannot be trusted to do it by default)	2024-11-03 19:19:15 -06:00
ext
models	repeat extend the prom to fill the initial tokens for nar-len (it somewhat works, the model just needs to train more)	2024-11-06 23:29:53 -06:00
utils
__init__.py
__main__.py	more adjustments (adjustments of early-exit entropy/varentropy thresholds, default rep pen being 1.5, experimental refine-on-stop, etc.)	2024-11-03 18:31:28 -06:00
config.py	more notes	2024-11-06 13:51:28 -06:00
data.py	saner mask creation? (it doesnt matter, kv cache wont work)	2024-11-02 21:00:21 -05:00
demo.py	more windows specific fixes, limit gradio to <5.0.0 on linux (it works on windows, but not on my linux machine tm)	2024-11-04 18:00:33 -06:00
export.py
inference.py	repeat extend the prom to fill the initial tokens for nar-len (it somewhat works, the model just needs to train more)	2024-11-06 23:29:53 -06:00
plot.py	very, very naive layerskip speculative sampling (it just checks if the current layer's state is good enough)	2024-11-02 11:49:05 -05:00
samplers.py	very, very naive layerskip speculative sampling (it just checks if the current layer's state is good enough)	2024-11-02 11:49:05 -05:00
train.py	eval fix for nar-len	2024-11-06 23:14:16 -06:00
webui.py	ugh	2024-11-06 23:16:28 -06:00