zwhe99/DeepMath-Omn-1.5B
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:May 22, 2025License:mitArchitecture:Transformer0.0K Open Weights Cold

DeepMath-Omn-1.5B is a 1.5 billion parameter language model developed by zwhe99, fine-tuned from nvidia/OpenMath-Nemotron-1.5B using reinforcement learning on the DeepMath-103K dataset. This model is specifically optimized for advanced mathematical reasoning, focusing on challenging problems across algebra, calculus, number theory, geometry, probability, and discrete mathematics. It aims to push the boundaries of mathematical problem-solving capabilities in LLMs, achieving state-of-the-art results on difficult math benchmarks.

Loading preview...