Francesco Bertolotti(@f14bertolotti):Stellar performance from a 3B model. These results were achieved primarily through post-training refinements on Qwen2.5-Coder. The paper doesn't provide many details, but it appears they distill from RL ckpts and then do a final RL-based instruct RL. 🔗https://t.co/FmdRwGNMOg

Francesco Bertolotti

@f14bertolotti

AI Researcher

加入 October 2021

141 正在關注 1.9K 粉絲

Francesco Bertolotti@f14bertolotti

2026.06.16 05:20

Stellar performance from a 3B model. These results were achieved primarily through post-training refinements on Qwen2.5-Coder. The paper doesn't provide many details, but it appears they distill from RL ckpts and then do a final RL-based instruct RL. 🔗