mrq 1a73ac6a20 I cannot believe it's not actually called Wand DB (added wandb logging support since I think it would have been a much better way to look at my metrics)		2024-11-20 16:10:47 -06:00
..
emb	fixes	2024-11-10 20:37:50 -06:00
engines	I cannot believe it's not actually called Wand DB (added wandb logging support since I think it would have been a much better way to look at my metrics)	2024-11-20 16:10:47 -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	added mixed modality AR+NAR-len to generate a short prefix through the AR, then inference with said prefix through the NAR-len (need to experiment with it more to ensure that the masked off tokens are the only tokens getting updated)	2024-11-20 14:22:12 -06:00
utils	default set cfg strength to 3.0 since the reference model is updated	2024-11-17 10:23:40 -06:00
__init__.py
__main__.py	better modality selection (pick AR+NAR by default for the ar+nar model, pick NAR-len by default for the nar-len model), lowered default CFG because it makes the AR+NAR output sped up (but can't be too low since it's required for the NAR-len)	2024-11-19 18:51:17 -06:00
config.py	I cannot believe it's not actually called Wand DB (added wandb logging support since I think it would have been a much better way to look at my metrics)	2024-11-20 16:10:47 -06:00
data.py	oops	2024-11-18 14:12:26 -06:00
demo.py	better modality selection (pick AR+NAR by default for the ar+nar model, pick NAR-len by default for the nar-len model), lowered default CFG because it makes the AR+NAR output sped up (but can't be too low since it's required for the NAR-len)	2024-11-19 18:51:17 -06:00
export.py	two weeks of agony concludes	2024-11-18 21:29:28 -06:00
inference.py	added mixed modality AR+NAR-len to generate a short prefix through the AR, then inference with said prefix through the NAR-len (need to experiment with it more to ensure that the masked off tokens are the only tokens getting updated)	2024-11-20 14:22:12 -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	cleaned up classifier-free guidance logit processing (in order to try and cope with a bad nar-len model)	2024-11-19 10:30:05 -06:00
train.py	default set cfg strength to 3.0 since the reference model is updated	2024-11-17 10:23:40 -06:00
webui.py	better modality selection (pick AR+NAR by default for the ar+nar model, pick NAR-len by default for the nar-len model), lowered default CFG because it makes the AR+NAR output sped up (but can't be too low since it's required for the NAR-len)	2024-11-19 18:51:17 -06:00