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
When you are wrestling for possession of a sword, the man with the handle always wins.
Recent Activity
liked a model 1 day ago
cudabenchmarktest/Qwen3.8-27B-E03-Obliterated-Omni-GGUF updated a model 1 day ago
cudabenchmarktest/Qwen3.8-27B-E03-Obliterated-Omni-GGUF published a model 1 day ago
cudabenchmarktest/Qwen3.8-27B-E03-Obliterated-Omni-GGUFOrganizations
None yet