mrq 3d6ef9666b overridden naive llama attention to get the right score values that entropix needs		2024-10-12 10:05:47 -05:00
..
arch	overridden naive llama attention to get the right score values that entropix needs	2024-10-12 10:05:47 -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	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
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	entropix tweaks (it doesn't output garbage but it loves to go for silence)	2024-10-12 09:46:18 -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
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