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 about 9 hours ago
VAST-AI/TripoSplat upvoted a collection about 9 hours ago
V-JEPA 2 upvoted a collection about 14 hours ago
VLA-JEPAOrganizations
None yet
models 16
cudabenchmarktest/stable-diffusion-3.5-large-turbo
Text-to-Image • Updated • 17
cudabenchmarktest/stable-audio-open-1.0
Text-to-Audio • 1B • Updated • 6
cudabenchmarktest/flux1-fill-dev-fp8
Image-to-Image • Updated • 1.26k
cudabenchmarktest/stable-diffusion-3.5-large
Updated
cudabenchmarktest/video-scan
Video-Text-to-Text • 2B • Updated • 16
cudabenchmarktest/qwen3.5-9b-r5-research-GGUF
Text Generation • 9B • Updated • 28
cudabenchmarktest/qwen3.5-9b-qwen3.6-reasoning-distilled-GGUF
Text Generation • 10B • Updated • 1.4k • 3
cudabenchmarktest/qwen3.5-9b-qwen3.6-reasoning-distilled
Text Generation • Updated • 266
cudabenchmarktest/qwen3.5-9b-r7-research-vision
Image-Text-to-Text • 9B • Updated • 3
cudabenchmarktest/qwen3.5-9b-r7-research
Text Generation • 9B • Updated • 8
datasets 6
cudabenchmarktest/r8b-tool-sft
Viewer • Updated • 1.6k • 32
cudabenchmarktest/r8-eval-suite-5bucket
Viewer • Updated • 192 • 81
cudabenchmarktest/r8-thinking-fix-sft
Viewer • Updated • 2.9k • 32
cudabenchmarktest/r7-additive-sft
Viewer • Updated • 4.04k • 85
cudabenchmarktest/r8-calibration-sft
Viewer • Updated • 7.64k • 126 • 1
cudabenchmarktest/r9-research-framework
Viewer • Updated • 1.55k • 239