mrq f97e8b0c7f ACTUALLY do KD-loss because of an oversight with masked_select outputting 1D tensors that get softmax'd in total		2024-12-07 09:52:51 -06:00
..
emb
engines	added knowledge distillation in the trainer (sadly it is not agnostic because of the grave mistake of further processing the batch within the forward pass, so subsequent calls do not match......)	2024-12-05 23:05:52 -06:00
models	agnostified KD	2024-12-06 23:53:46 -06:00
utils	agnostified KD	2024-12-06 23:53:46 -06:00
__init__.py
__main__.py	actually fixed knowledge distillation because of errant -inf logits causing problems and needed to be filtered (and splitting text language / output audio language because it helps)	2024-12-06 21:55:20 -06:00
config.py	ACTUALLY do KD-loss because of an oversight with masked_select outputting 1D tensors that get softmax'd in total	2024-12-07 09:52:51 -06:00
data.py	oops	2024-12-04 21:24:22 -06:00
demo.py
export.py
inference.py	actually fixed knowledge distillation because of errant -inf logits causing problems and needed to be filtered (and splitting text language / output audio language because it helps)	2024-12-06 21:55:20 -06:00
plot.py
samplers.py
train.py	ACTUALLY do KD-loss because of an oversight with masked_select outputting 1D tensors that get softmax'd in total	2024-12-07 09:52:51 -06:00
webui.py	actually fixed knowledge distillation because of errant -inf logits causing problems and needed to be filtered (and splitting text language / output audio language because it helps)	2024-12-06 21:55:20 -06:00