CoolFace
Modelpublic

hudsongouge/qwen35-9b-nvfp4-podcast-cleaner-grpo

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes8downloads
Model Card

qwen35-9b-nvfp4-podcast-cleaner-grpo

Merged NVFP4 (llm-compressor) checkpoint of the GRPO LoRA for vLLM.

MetricThink-SFTGRPO
json_ok69.8%81.0%
think_closed73.0%87.3%
mean_jaccard0.1750.240
hit_max30.2%17.5%

LoRA source: hudsongouge/qwen35-9b-grpo-rescue