At the Wix Data Science group, we explore various fine-tuning techniques to adapt LLMs for Wix's unique needs.
In this talk, We'll discuss our journey, including the development of a small Wix LLM (based on LLaMa 7B) that performed better than GPT-3.5 in various Wix tasks such as: question answering, intent classification and ticket summarization. This work highlights how to create and evaluate custom LLMs for specific tasks, potentially reducing costs and complexity while maintaining accuracy.
You can also read Lior's blog post "Customizing LLMs for Enterprise Data Using Domain Adaptation: The Wix Journey" here:
www.wix.engineering/post/customizing-llms-for-ente…
コメント