NanoCode012 b2a8c37a27 fix: use smaller model

2025-08-12 20:34:47 +07:00

..

glm4.5-qlora.yaml

fix: use smaller model

2025-08-12 20:34:47 +07:00

qlora-32b.yaml

use warmup_ratio as a better default than warmup steps since it's data dependent (#2897) [skip ci]

2025-07-30 06:44:06 -04:00