mrq ec79230965 shuffled web UI options hidden by cfg.experimental to its own tab, expose early exit selection to inferencing (it kinda works naively, still need to implement self-speculation)		2024-11-01 21:30:06 -05:00
..
emb
engines	skip step on nan loss (ironically I have not had a nan loss after adding this), throw exception with invalid cfg.dataset.sample_type and sample_order combination (because I was tricked by this in my yaml and had inconsistent vram usage)	2024-11-01 20:54:53 -05:00
ext
models	shuffled web UI options hidden by cfg.experimental to its own tab, expose early exit selection to inferencing (it kinda works naively, still need to implement self-speculation)	2024-11-01 21:30:06 -05:00
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
__main__.py	shuffled web UI options hidden by cfg.experimental to its own tab, expose early exit selection to inferencing (it kinda works naively, still need to implement self-speculation)	2024-11-01 21:30:06 -05:00
config.py	actually float16(+AMP) and layerskip is bad and will kill the model......	2024-11-01 18:36:44 -05:00
data.py	skip step on nan loss (ironically I have not had a nan loss after adding this), throw exception with invalid cfg.dataset.sample_type and sample_order combination (because I was tricked by this in my yaml and had inconsistent vram usage)	2024-11-01 20:54:53 -05:00
demo.py	layer skip training implemented (need to gut the inferencing from the repo, and to actually see if the model can benefit from this)	2024-10-30 20:05:45 -05:00
export.py
inference.py	shuffled web UI options hidden by cfg.experimental to its own tab, expose early exit selection to inferencing (it kinda works naively, still need to implement self-speculation)	2024-11-01 21:30:06 -05:00
plot.py	too brainlet to diagnose why low temp / greedy sampling is randomly unstable some of the time	2024-10-22 20:13:54 -05:00
samplers.py	actually have beam_width in the webUI work	2024-10-22 22:06:22 -05:00
train.py	actually float16(+AMP) and layerskip is bad and will kill the model......	2024-11-01 18:36:44 -05:00
webui.py	shuffled web UI options hidden by cfg.experimental to its own tab, expose early exit selection to inferencing (it kinda works naively, still need to implement self-speculation)	2024-11-01 21:30:06 -05:00