QED-Nano: Teaching a Tiny Model to Prove Hard Theorems
📝
87
Who needs 1T parameters? Olympiad proofs with a 4B model
ruins
ruinnight
webbrain-one-939230's profile picture
archinovo's profile picture
webbrain-one-503037's profile picture·
AI & ML interests
None yet
Organizations
None yet
liked a
Space 9 months ago
liked 3
Spaces about 1 year ago
Unlocking On-Policy Distillation for Any Model Family
📝
123
Explore on‑policy distillation visualizations for any model
Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks
📝
96
Evaluate multilingual models using FineTasks
The Smol Training Playbook
📚
3.37k
The secrets to building world-class LLMs
liked 3
models about 1 year ago
liked a
dataset about 1 year ago
liked a
dataset over 1 year ago