使用QLORA微调Llama 3.1 8B
原文英文,约1400词,阅读约需5分钟。发表于: 。Large Language Models (LLMs) are fantastic tools for getting quick answers on programming questions. However, their knowledge is not always up to date and they may not know about your favourite...
大型语言模型(LLMs)可以快速解决编程问题,但可能缺乏最新知识。本文介绍如何通过微调Meta的Llama 3.1 8B模型,使其能回答苹果新深度学习框架MLX的问题。使用QLORA方法微调,降低GPU内存和训练时间,并在Koyeb的无服务器GPU上部署。需要Python、OpenAI API和HuggingFace权限。