mrq 07f8e2ad06 added option to set the causal size (how many tokens to sample per AR step), but requires the model to be trained for this (which explains why recurrent chunk sampling just doesn't work for the retnet tests, obvious in hindsight)		2024-07-30 20:53:51 -05:00
..
arch	mamba2-hf using vasqu/mamba2-torch because it lets me use mamba2 without triton ops (training with my 4xV100s are not happy with mamba2 because of triton)	2024-06-14 19:42:17 -05:00
__init__.py	sanity cleanup: moved experimental features under its own thing	2024-06-30 10:37:33 -05:00
ar_nar.py	added option to set the causal size (how many tokens to sample per AR step), but requires the model to be trained for this (which explains why recurrent chunk sampling just doesn't work for the retnet tests, obvious in hindsight)	2024-07-30 20:53:51 -05:00
base.py	added option to set the causal size (how many tokens to sample per AR step), but requires the model to be trained for this (which explains why recurrent chunk sampling just doesn't work for the retnet tests, obvious in hindsight)	2024-07-30 20:53:51 -05:00
experimental.py	added what I think is DRY sampling	2024-07-29 19:15:07 -05:00
lora.py	some weird fixes for an equally weird regression with LoRA loading	2024-07-22 20:47:24 -05:00
nar.py	sanity cleanups with weird off-by-one-ness, cleaned up and validated vall_e.models.experimental works again	2024-07-27 15:36:05 -05:00