大语言模型生成式AI学习笔记——2. 2.5PEFT（参数高效微调）——实验2（对话总结生成式AI模型的调优）

Lab 2 - Fine-tune a generative AI model for dialogue summarization（对话总结生成式AI模型的调优）

In this notebook, you will fine-tune an existing LLM from Hugging Face for enhanced dialogue summarization. You will use the FLAN-T5 model, which provides a high quality instruction tuned model and can summarize text out of the box. To improve the inferences, you will explore a full fine-tuning approach and evaluate the results with ROUGE metrics. Then you will perform PEFT fine-tuning, evaluate the resulting model and see that the benefits of PEFT outweigh the slightly-lower performance metrics.

 Note: For the lab, it is better to use a laptop or desktop computer instead of a tablet. 

The labs in this course are accessible to learners who have paid for the course. If you have not yet purchased access, click the "Upgrade to Submit" button below to purchase the course and view the lab.

If you have already paid for the course, start the lab by first ticking the checkbox below indicating you will adhere to the Coursera Honor Code, then click on the "Launch App" button.

The lab is formally ungraded, but you will need to click on the Submit button to complete the lab.

Please refer to this topic in our community platform for common questions and troubleshooting regarding the labs. If you can't view it, please create an account following the instructions

here, then click on the topic again.

在本笔记本中，您将对Hugging Face的现有LLM进行微调，以提高对话摘要的能力。您将使用FLAN-T5模型，该模型提供了一个高质量的指令调整模型，并且能够直接对文本进行摘要。为了提升推理能力，您将探索完整的微调方法，并使用ROUGE指标评估结果。然后，您将执行PEFT微调，评估得到的模型，并发现PEFT的好处超过了稍微低一些的性能指标。

注意：对于实验室，最好使用笔记本电脑或台式电脑，而不是平板电脑。

本课程中的实验室仅对已购买课程的学习者开放。如果您还没有购买访问权限，请点击下方的"升级以提交"按钮购买课程并查看实验室。

如果您已经购买了课程，请首先勾选下面的复选框，表明您将遵守Coursera荣誉守则，然后点击"启动应用"按钮开始实验室。

实验室不进行正式评分，但您需要点击提交按钮以完成实验室。

关于实验室的常见问题和故障排除，请参阅我们社区平台中的这个话题。如果您无法查看，请按照此处的说明创建一个帐户，然后再次点击该话题。