mmoselhy077

qwen3-8b-sva-codev2k-s42-lora

mmoselhy077/qwen3-8b-sva-codev2k-s42-lora

qwen3-8b-sva-codev2k-s42-lora is a machine learning model from mmoselhy077. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.

CodeV re-distill scale-up +2k arm (2093 CodeV rows, 78% of corpus). Qwen3-8B LoRA (r64/a128, 3ep). full-356 equiv pass@1 = 44.1% — NO-GO (base922 baseline 51.5%). Regression is intrinsic to the CodeV distribution, not…