mrq 29e45be0b4 tweaks to bucket sampling		2024-11-13 11:09:24 -06:00
..
emb	fixes	2024-11-10 20:37:50 -06:00
engines	fixes	2024-11-10 20:37:50 -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	better causal-ness for split loss calc, and also do masking for NAR-len for it	2024-11-13 10:17:52 -06:00
utils	tweaks to bucket sampling	2024-11-13 11:09:24 -06:00
__init__.py
__main__.py	new meme sampler PogChamp new meme sampler PogChamp (it sort of helps?)	2024-11-12 22:30:09 -06:00
config.py	overhauled inference/sampler kwargs to stop being a bloated mess	2024-11-11 20:21:16 -06:00
data.py	resume iteration step in tqdm trainer, warn to logger if the sampler state dict was invalidated	2024-11-13 09:09:28 -06:00
demo.py	new meme sampler PogChamp new meme sampler PogChamp (it sort of helps?)	2024-11-12 22:30:09 -06:00
export.py	tweaks and fixes for lora stuffs	2024-09-08 18:05:21 -05:00
inference.py	overhauled inference/sampler kwargs to stop being a bloated mess	2024-11-11 20:21:16 -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	new meme sampler PogChamp new meme sampler PogChamp (it sort of helps?)	2024-11-12 22:30:09 -06:00
train.py	dropped subtrain dataloader since its useless to duplicate	2024-11-11 17:00:49 -06:00
webui.py	NAR-len RVQ-0 was being trained causally.............	2024-11-13 09:43:50 -06:00