abinzzz/ForeLen

ForeLen是一个全面的基准测试，旨在评估大型语言模型（LLM）的输出长度预测能力。它包括长序列、链式思维（CoT）和强化学习（RL）采样数据，使得社区能够严格测试静态和动态长度预测器。

ForeLen is a comprehensive benchmark designed to evaluate the output length prediction capability of Large Language Models (LLM). It includes long-sequence, Chain-of-Thought (CoT), and reinforcement learning (RL) sampling data, enabling the community to rigorously test both static and dynamic length predictors.