We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.
Introduction
我们推出了一种新型模型，专门为代码生成任务而设计。在HumanEval基准数据集上，其测试准确性超过了GPT-4 Turbo（2024年4月版）和GPT-4o。【此简介由AI生成】
Apache-2.0 Python48Commitscode-generationcode-interpreterhumanevalllmnlpnlp-machine-learningtext-generation
Customize your domain