Learn how to improve the performance of Llama3 8B on the Spider dataset using various prompting strategies and fine-tuning.
•11m read time• From databricks.com
Table of contents
Zero-shot Prompting for Baseline PerformancePrompting With Sample RowsFew-shot PromptingFine-Tuning with LoRADeploy to a Model Serving EndpointWrapping UpAppendixSort: