mrq 48461833c2 ugh		2024-10-15 19:30:43 -05:00
..
emb	added experimental entropix sampling support	2024-10-11 21:18:26 -05:00
engines	ugh	2024-09-18 21:40:57 -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	entropix apparently processes the entire sequence of logits but it falls apart when doing that	2024-10-13 12:01:12 -05:00
utils	sped up inferencing by not doing .tolist() for rep pen / length pen (and a bug fix in the web UI from prev commit)	2024-10-04 22:18:20 -05:00
__init__.py	Rewrite init	2023-08-02 21:53:35 +00:00
__main__.py	modified demo page to be more modular with demoing comparisons, actually provide a path to use modified naive attention, entropix sampling is not tied to an experimental yaml flag now	2024-10-12 11:27:55 -05:00
config.py	modified demo page to be more modular with demoing comparisons, actually provide a path to use modified naive attention, entropix sampling is not tied to an experimental yaml flag now	2024-10-12 11:27:55 -05:00
data.py	added experimental entropix sampling support	2024-10-11 21:18:26 -05:00
demo.py	output attention scores for SDPA/flash, since naive attention seems broken	2024-10-12 12:09:17 -05:00
export.py	tweaks and fixes for lora stuffs	2024-09-08 18:05:21 -05:00
inference.py	ugh	2024-10-15 19:30:43 -05:00
plot.py	lol	2024-10-12 09:57:34 -05:00
samplers.py	entropix apparently processes the entire sequence of logits but it falls apart when doing that	2024-10-13 12:01:12 -05:00
train.py	added --eval-random-text-prompts to use random text prompts for eval pass, added --random-prompts for demo page and --lora to use a sample with the lora disabled, probably finally fixed validation dataloader breaking on eval	2024-10-10 13:40:25 -05:00
webui.py	kludge fix for an oversight in the model when trying to train for longer input prompt durations......	2024-10-15 19:25:03 -05:00