QED-Nano: Teaching a Tiny Model to Prove Hard Theorems
📝
45
Who needs 1T parameters? Olympiad proofs with a 4B model
ruins
ruinnight
AI & ML interests
None yet
Recent Activity
liked
a Space about 17 hours ago
lm-provers/qed-nano-blogpost upvoted an article about 1 month ago
Why We Built VIBE Bench: Rethinking Evaluation for Real Workloads upvoted an article about 1 month ago
M2.1: Multilingual and Multi-Task Coding with Strong Generalization Organizations
None yet
liked a Space about 17 hours ago
liked 3 Spaces 4 months ago
Unlocking On-Policy Distillation for Any Model Family
📝
86
Visualize on-policy distillation for any model family
Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks
📝
88
Evaluate multilingual models using FineTasks
The Smol Training Playbook
📚
3.01k
The secrets to building world-class LLMs
liked 3 models 6 months ago
liked a dataset 6 months ago
liked a dataset 10 months ago