PlanePaper/LEAD-7B
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:May 4, 2025License:apache-2.0Architecture:Transformer Open Weights Cold

PlanePaper/LEAD-7B is a 7.6 billion parameter language model fine-tuned using the GRPO-LEAD reinforcement learning pipeline, specifically optimized for efficient and accurate mathematical reasoning. This model achieves superior consistency and accuracy on AIME24 and AIME25 datasets, demonstrating significantly shorter average reasoning lengths compared to other 14B models. With a context length of 131072 tokens, it is designed for challenging mathematical problem-solving scenarios.

Loading preview...