Qwen3.5-9B LoRA SFT distillation: R7 (86.8% eval) + R8 calibration. Datasets, FP16 checkpoints, and pipeline docs.
🔄 In a Training Loop
lee
cudabenchmarktest
AI & ML interests
How incredible it is to be anything at all
Recent Activity
liked a model 2 days ago
Qwen/Qwen3.8-Flash-Next updated a dataset 5 days ago
cudabenchmarktest/opaque-agent-calibration-1000-baseline published a dataset 5 days ago
cudabenchmarktest/opaque-agent-calibration-1000-baselineOrganizations
None yet