Running Featured 82 QED-Nano: Teaching a Tiny Model to Prove Hard Theorems ๐ 82 Who needs 1T parameters? Olympiad proofs with a 4B model
meta-llama/Llama-3.2-3B-Instruct Text Generation โข 3B โข Updated Oct 24, 2024 โข 1.46M โข โข 2.39k