almogtavor / SE-KD3x
PublicEfficient LLM distillation via student-entropy selection across three axes.
SE-KD3X enables efficient training of smaller language models by selectively distilling knowledge from larger teacher models, focusing on high-uncertainty tokens for major speed and memory savings.
How It Works
You find a smart way to train smaller AI assistants by copying only the most helpful lessons from bigger ones, saving time and computer power.
You add the simple kit to your computer with one easy command.
Pick a big expert AI to learn from and a smaller one to improve, plus some example texts to practice on.
Hit go, and it automatically focuses on the trickiest parts where the small AI needs the most help, training way faster.
See your training finish quicker with less memory used, while getting great results.
Run quick checks to confirm your smaller AI performs as well or better.
Celebrate having a fast, smart assistant that rivals the big ones but runs on everyday hardware.
Star Growth
Repurpose is a Pro feature
Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.
Unlock RepurposeSimilar repos coming soon.