Qwen3.5-9B R-Series Distillation
Collection
Qwen3.5-9B LoRA SFT distillation: R7 (86.8% eval) + R8 calibration. Datasets, FP16 checkpoints, and pipeline docs. • 5 items • Updated
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
updated a collection about 6 hours ago
Qwen3.5-9B R-Series Distillation updated a collection about 6 hours ago
Qwen3.5-9B R-Series Distillation updated a collection about 6 hours ago
Qwen3.5-9B R-Series DistillationOrganizations
None yet
updated a
collection about 6 hours ago
updated a
dataset about 6 hours ago
published a
dataset about 6 hours ago
liked a
model about 6 hours ago
updated a
dataset about 7 hours ago
published a
dataset about 7 hours ago
updated a
model about 10 hours ago
updated a
model about 12 hours ago
updated 3
models about 13 hours ago
published 2
models about 14 hours ago
published a
model 3 days ago
liked a
dataset 5 days ago
liked a
model 5 days ago
