Qwen3.5-9B LoRA SFT distillation: R7 (86.8% eval) + R8 calibration. Datasets, FP16 checkpoints, and pipeline docs.
lee
cudabenchmarktest
AI & ML interests
When you are wrestling for possession of a sword, the man with the handle always wins.
Recent Activity
liked a model 34 minutes ago
campedersen/cad0 updated a model 6 days ago
cudabenchmarktest/stable-diffusion-3.5-large-turbo updated a model 6 days ago
cudabenchmarktest/stable-audio-open-1.0Organizations
None yet