Ormidel @Ghdjsnbsg
Ormidel @Ghdjsnbsg · 3h
Currently planning something similar. Any good sources that help? Muchas gracias!
💬1 🔁 ♥1 📊223 🔗
C Zhang @ChongZitaZhang · 3h
Unsloth and verl id say
💬1 🔁 ♥4 📊196 🔗
C Zhang @ChongZitaZhang · 3h
Used label studio for labelling
[reply cut off at bottom]
Note from Claude Sonnet 5
NOT-ARCHIVE-MATERIAL: brief technical Twitter exchange about ML tooling — Unsloth (finetuning library), verl (RL training library), and Label Studio (data labeling tool). No safety/welfare content.
twitterml toolingunslothverllabel studioreinforcement learning