mrq acdce66d4e readme tweaks, set the (unused) default model download URL back to the base ar+nar-llama-8 model, as ar+nar-tts+stt-llama-8 was renamed back to it since it performs well		2024-10-05 22:53:53 -05:00
..
arch	ugh	2024-08-30 14:39:07 -05:00
__init__.py	readme tweaks, set the (unused) default model download URL back to the base ar+nar-llama-8 model, as ar+nar-tts+stt-llama-8 was renamed back to it since it performs well	2024-10-05 22:53:53 -05:00
ar_nar.py	readme tweaks, set the (unused) default model download URL back to the base ar+nar-llama-8 model, as ar+nar-tts+stt-llama-8 was renamed back to it since it performs well	2024-10-05 22:53:53 -05:00
ar.py	experimental implementation of STT (need to actually test on a model, test trainer seems to work)	2024-09-05 20:43:20 -05:00
base.py	readme tweaks, set the (unused) default model download URL back to the base ar+nar-llama-8 model, as ar+nar-tts+stt-llama-8 was renamed back to it since it performs well	2024-10-05 22:53:53 -05:00
experimental.py	moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)	2024-08-29 13:27:16 -05:00
lora.py	naive model offloading support (handles automatically splitting parts of the model to requested device per memory constraints, either inferred or requested in the yaml, input tensors are automatically migrated to the right device, it SEEMS to work for training under the test trainer when split between GPU and CPU) (this was specifically only because that Flux imagegen model released so I can test it there)	2024-08-01 20:12:06 -05:00
nar.py	experimental implementation of STT (need to actually test on a model, test trainer seems to work)	2024-09-05 20:43:20 -05:00