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
ext
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
__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 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
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
samplers.py
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