@jenzhuscott
The whales π is back! DeepSeek-Math-V2: 685B-parameter math monster built on V3.2-Exp-Base, fully open under Apache 2.0 - 1st model to use a generator-verifier loop in training: writes proofs β verifier scores them β RL closes the loop for self-verifiable reasoning. - Focuses on verifiable full proofs, not just final answers - huge leap for formal theorem proving. - Trained w automatic high-compute verification runs to create its own high-quality proof data at scale Enjoy π π https://t.co/0SlhCibvP3