CoolFace
Modelpublic

zqmalyssa/Qwen2.5-1.5B-Assistant

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes52downloads
Model Card

A lightweight model fine-tuned from Qwen2.5-1.5B via SFT and DPO alignment. Enjoy!

PhaseMetricValue
SFTFinal Loss1.65
DPOAccuracies70.4%
DPOMargins1.022