In a Training Loop 🔄

lee

cudabenchmarktest

AI & ML interests

Lee is exploring fine tuning of small language models, specifically in reducing thinking tokens while maintaining quality chain of thought, refusal and abliteration, along with novel reasoning distillation techniques.

Recent Activity

updated a collection about 3 hours ago

Qwen3.5-9B R-Series Distillation

updated a collection about 3 hours ago

Qwen3.5-9B R-Series Distillation

updated a collection about 3 hours ago

Qwen3.5-9B R-Series Distillation

View all activity

Organizations

None yet

liked a model about 3 hours ago

OBLITERATUS/Qwen3-4B-OBLITERATED

4B • Updated 24 days ago • 269 • 5

liked a dataset 5 days ago

khazarai/Multi-Domain-Reasoning-Benchmark

Viewer • Updated 2 days ago • 100 • 182 • 3

liked 2 models 5 days ago

z-lab/Qwen3.5-9B-DFlash

Text Generation • 1B • Updated 7 days ago • 7.22k • 19

khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled-GGUF

Text Generation • 4B • Updated 5 days ago • 26.4k • 20

liked a model 8 days ago

YatharthS/LuxTTS

Text-to-Speech • Updated Jan 23 • 8.21k • 187

lee

AI & ML interests

Recent Activity

Organizations

cudabenchmarktest's activity