Safurai-Csharp:利用合成数据改进特定语言的代码大语言模型
Safurai-Csharp: Harnessing Synthetic Data to improve language-specific Code LLM
AI总结:
本研究推出专注C#代码任务的开源模型Safurai-Csharp,基于CodeLlama 34B结合EvolInstruct技术用合成扩充数据微调,在Manual MultiPL-E零样本Pass@1基准上获56.33%得分,助力开发者工作与代码学习,推动特定语言代码LLM发展。
摘要:
本文介绍了Safurai-Csharp,这是一款专为C#代码生成、补全和调试打造的开源模型。该模型基于全新的CodeLlama 34B模型构建,运用EvolInstruct技术创建了经过优化扩充的数据集用于微调过程。其性能结果显示,在Manual MultiPL-E基准(零样本,Pass@1)上取得了56.33%的突出得分,表明该模型具备高效简化开发者工作流程、辅助代码学习的强大能力。它有望在开源C#大语言模型领域树立新标杆,并推动特定语言大语言模型领域更具包容性、更广泛的发展。
英文摘要:
This paper introduces Safurai-Csharp, an open-source model designed to specialize in the generation, completion, and debugging of C# code. Safurai-Csharp is built upon the novel CodeLlama 34B model and leverages the EvolInstruct technique, creating a refined and expanded dataset for its fine-tuning process. The results of its performance, a notable score of 56.33% on the Manual MultiPL-E benchmark (Zero-Shot, Pass@1), signal its high capacity to streamline developers' workflows and aid code learning. It shows promise in setting new stakes in the landscape of open-source C# LLMs and hopes to inspire more inclusive and wide-ranging development in the field of language-specific LLMs.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。