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
75b90be325
cleaned up unused config flags, allow less strict yaml by pruning missing keys, renamed some dataset configs to be more unified
f88097ccf6
add config option to set the rate of sampling randomly vs similar speakers during training
eea70f5698
kludge fix for an oversight in the model when trying to train for longer input prompt durations......
84005c5b00
entropix apparently processes the entire sequence of logits but it falls apart when doing that
c800d28bb8
respect attention defined in the yaml for web UI (which might explain why theres been a discrepancy in outputs for me)
04e983b86b
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
d0ab7d755a
added min-p (really does not seem useful since it's very sensitive), more tweaks to entropix