mrq 943fe70c10 I don't know why this fixes an assert thrown but it does		2024-11-09 19:04:13 -06:00
..
emb	ugh	2024-11-05 11:50:05 -06:00
engines	new NAR-len training paradigm......	2024-11-07 11:32:11 -06:00
ext	maybe final tweaks, I really needed to unify my json read/write and orjson is proven to be fast enough for me to try and rely on it more	2024-09-17 22:57:04 -05:00
models	I don't know why this fixes an assert thrown but it does	2024-11-09 19:04:13 -06:00
utils	modified default arguments (ar temp = 0 and rep pen = 1.125 seems to be stable, at least given the few things i tested), do not pass top k/top p/min p to NAR even though technically none of those things should matter when greedy sampling	2024-10-22 18:12:39 -05:00
__init__.py	Rewrite init	2023-08-02 21:53:35 +00:00
__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	This better work	2024-11-09 18:04:59 -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	tweaks and fixes for lora stuffs	2024-09-08 18:05:21 -05:00
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	Something's Wrong	2024-11-09 15:07:43 -06:00
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