mrq b09328069e actually do CFG sampling for base AR+NAR tasks		2024-11-12 13:42:39 -06:00
..
arch	This better work	2024-11-09 18:04:59 -06:00
__init__.py	unified nar.py into ar_nar.py	2024-11-10 12:19:48 -06:00
ar_nar.py	actually do CFG sampling for base AR+NAR tasks	2024-11-12 13:42:39 -06:00
base.py	actually fixed rep pen (for ar and nar, it seems to help with nar unmasking)	2024-11-11 21:40:19 -06:00
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