mrq
-
https://git.ecker.tech/ aims to provide a place to share my efforts while maintaining true ownership of my code, as I do not trust GitHub.
XMR: 4B9TQdkAkBFYrbj5ztvTx89e5LpucPeTSPzemCihdDi9EBnx7btn8RDNZTBz2zihWsjMnDkzn5As1LU6gLv3KQy8BLsZ8SG
- Joined on
2022-10-10
Block a user
ad7e290a5e
ugh (ROCm seems to silently clamp any token value >= logits.shape[-1] for loss calculation, while cuda will throw an assert, making it hard to find this dumb fuckup)
dcd5fecff3
some cleanup while I wait for the NAR-len to train to an acceptable state (currently it performs okay, but only on audo after 3 seconds or so)
69b0b3b854
set timestep tensor to whatever the time embedding's dtype is because it'll gripe under amp
811b15d280
I suppose I just have a shit training method since the sampler is as solid as I can get it...............
c127c4e488
'borrowed' a sampling scheduler for NAR-len's RVQ level 0 (better than before, but still not good enough)
d17f0ebc7c
'borrowed' a sampling scheduler for NAR-len's RVQ level 0 (better than before, but still not good enough)