mrq c690aa509d fixes and compat (MoE-fying an existing model and retraining from there just ruins it after a second of audio...)		2023-12-25 21:20:32 -06:00
..
emb	added sampling by speaker group name (might be better to de-emphasize the LibriVox/Audiobooks that are in large numbers, and emphasize the smaller pools), log cleanup	2023-10-16 19:30:38 -05:00
engines	fixes and compat (MoE-fying an existing model and retraining from there just ruins it after a second of audio...)	2023-12-25 21:20:32 -06:00
models	fixes and compat (MoE-fying an existing model and retraining from there just ruins it after a second of audio...)	2023-12-25 21:20:32 -06:00
utils	added torchscale XMOE integration (because Mixtral 8x7B seems very promising and I want to see if it works)	2023-12-20 18:45:58 -06:00
__init__.py
__main__.py	exposed rolling resp context to the web UI, added passing in language to inferencing command line	2023-10-12 23:21:01 -05:00
config.py	fixes and compat (MoE-fying an existing model and retraining from there just ruins it after a second of audio...)	2023-12-25 21:20:32 -06:00
data.py	added torchscale XMOE integration (because Mixtral 8x7B seems very promising and I want to see if it works)	2023-12-20 18:45:58 -06:00
export.py
inference.py	fixes and compat (MoE-fying an existing model and retraining from there just ruins it after a second of audio...)	2023-12-25 21:20:32 -06:00
plot.py
samplers.py	separated samplers into its own file, don't bother copying the logits back to the GPU after sampling, it's not necessary	2023-10-11 12:25:31 -05:00
train.py	evaluation/validation passes language ID during training (oops)	2023-10-29 12:00:40 -05:00
webui.py	added torchscale XMOE integration (because Mixtral 8x7B seems very promising and I want to see if it works)	2023-12-20 18:45:58 -06:00