Phase 2: reasoning SFT Collection Reasoning SFT on 30K samples of OpenThoughts3 (OT30K) or another reasoning dataset, and the checkpoints each run starts from. • 96 items • Updated 2 days ago
Phase 2: reasoning SFT Collection Reasoning SFT on 30K samples of OpenThoughts3 (OT30K) or another reasoning dataset, and the checkpoints each run starts from. • 96 items • Updated 2 days ago