mrq 70cf694cfd output attention scores for SDPA/flash, since naive attention seems broken		2024-10-12 12:09:17 -05:00
..
arch	output attention scores for SDPA/flash, since naive attention seems broken	2024-10-12 12:09:17 -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	modified demo page to be more modular with demoing comparisons, actually provide a path to use modified naive attention, entropix sampling is not tied to an experimental yaml flag now	2024-10-12 11:27:55 -05:00
ar.py	added min-p (really does not seem useful since it's very sensitive), more tweaks to entropix	2024-10-11 22:36:06 -05:00
base.py	modified demo page to be more modular with demoing comparisons, actually provide a path to use modified naive attention, entropix sampling is not tied to an experimental yaml flag now	2024-10-12 11:27:55 -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	added min-p (really does not seem useful since it's very sensitive), more tweaks to entropix	2024-10-11 22:36:06 -05:00