Qwen3.5-9B LoRA SFT distillation: R7 (86.8% eval) + R8 calibration. Datasets, FP16 checkpoints, and pipeline docs.
lee
cudabenchmarktest
AI & ML interests
Finetuning small language models, maintaining quality chain of thought, refusal and abliteration, along with novel reasoning distillation techniques. When you are wrestling for possession of a sword, the man with the handle always wins.
Recent Activity
liked a dataset 3 days ago
caiovicentino1/Qwen3.6-35B-A3B-mcr-stage-b liked a model 3 days ago
Jackrong/Qwopus-GLM-18B-Merged-GGUF liked a model 4 days ago
unsloth/GLM-5.1-GGUFOrganizations
None yet
models 11
cudabenchmarktest/qwen3.5-9b-r5-research-GGUF
Text Generation • 9B • Updated • 1.21k
cudabenchmarktest/qwen3.5-9b-qwen3.6-reasoning-distilled-GGUF
Text Generation • 10B • Updated • 7.4k • 1
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 • 34
cudabenchmarktest/qwen3.5-9b-r7-research
Text Generation • 9B • Updated • 477
cudabenchmarktest/personaplex-7b-nf4-distilled
Updated
cudabenchmarktest/personaplex-7b-hybrid
Updated
cudabenchmarktest/personaplex-7b-nf4
Updated • 83
cudabenchmarktest/personaplex-7b-turbo2bit
Updated • 154 • 4
cudabenchmarktest/Qwen3.5-27B-turbo2bit
8B • Updated • 22
datasets 6
cudabenchmarktest/r8b-tool-sft
Viewer • Updated • 1.6k • 46
cudabenchmarktest/r8-eval-suite-5bucket
Viewer • Updated • 192 • 74
cudabenchmarktest/r8-thinking-fix-sft
Viewer • Updated • 2.9k • 54
cudabenchmarktest/r7-additive-sft
Viewer • Updated • 4.04k • 47
cudabenchmarktest/r8-calibration-sft
Viewer • Updated • 7.64k • 57
cudabenchmarktest/r9-research-framework
Viewer • Updated • 1.55k • 145