mrq d229725c76 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
..
emb	saner mask creation? (it doesnt matter, kv cache wont work)	2024-11-02 21:00:21 -05:00
engines	ughh	2024-11-01 22:36:48 -05:00
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	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
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	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
data.py	saner mask creation? (it doesnt matter, kv cache wont work)	2024-11-02 21:00:21 -05:00
demo.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
export.py	tweaks and fixes for lora stuffs	2024-09-08 18:05:21 -05:00
inference.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
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	changed layerskip float16 training warning (since it didnt seem to fry on my 4xV100 system)	2024-11-03 09:58:29 -06:00
webui.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