mrq 4d2b88b164 throw exception if training, but no model is set to train (because i ran into this wondering what the hell was happening)		2024-08-03 20:51:23 -05:00
..
emb	added prom-less training / inferencing, some other things	2024-07-22 19:36:07 -05:00
engines	tweaks for the NAR-len model, maybe	2024-08-03 08:40:39 -05:00
ext	fixes	2024-06-04 00:07:00 -05:00
models	more coping with the NAR len	2024-08-03 20:23:36 -05:00
utils	throw exception if training, but no model is set to train (because i ran into this wondering what the hell was happening)	2024-08-03 20:51:23 -05:00
__init__.py	Rewrite init	2023-08-02 21:53:35 +00:00
__main__.py	added option to set the causal size (how many tokens to sample per AR step), but requires the model to be trained for this (which explains why recurrent chunk sampling just doesn't work for the retnet tests, obvious in hindsight)	2024-07-30 20:53:51 -05:00
config.py	some cleanup, fixed the wrapper attention to explicitly use other sdpa backends	2024-08-03 19:51:00 -05:00
data.py	fixes, throw an exception when using NAR only model with non-unified position IDs, since for some reason it outputs garbage for the NAR	2024-08-02 22:25:49 -05:00
demo.py	actually pass language into dataset process script, fix coercing japanese into hiragana because espeak does not like kanji	2024-07-21 23:21:37 -05:00
export.py	fix weird regression in handling checkpoints when backend is local, but deepspeed checkpoints are in (it was handled with LoRA loading but not real loading...)	2024-07-30 22:15:56 -05:00
inference.py	fix weird regression in handling checkpoints when backend is local, but deepspeed checkpoints are in (it was handled with LoRA loading but not real loading...)	2024-07-30 22:15:56 -05:00
plot.py	ugh	2024-06-09 11:39:43 -05:00
samplers.py	possible speedup for samplers that require a list of previous tokens (the DRY sampler made me realize that I should copy the tolist() thing from the rep pen sampler for everything else)	2024-07-29 20:23:26 -05:00
train.py	sanity cleanups with weird off-by-one-ness, cleaned up and validated vall_e.models.experimental works again	2024-07-27 15:36:05 -05:00
webui.py	added option to set the causal size (how many tokens to sample per AR step), but requires the model to be trained for this (which explains why recurrent chunk sampling just doesn't work for the retnet tests, obvious in hindsight)	2024-07-30 20:53:51 -05:00