sparse-neural-networks

[Update] Project Nord: Solved the "Empty Wallet" Problem via Decentralized SNN Merging. Scaling to 10B is now possible. [R]

Project Nord, a 1.088B SNN model, has overcome its training budget limitation thanks to a breakthrough decentralized merging solution from the open-source community. A developer implemented a Sparse-Aware / OR-Set merge logic based on CRDTs, preserving signal in sparse models and enabling scaling to 10B.