From the course: Fine-Tune Your LLMs
Join today to access over 24,900 courses taught by industry experts.
Challenge: Develop a chatbot based on a fine-tuned model
From the course: Fine-Tune Your LLMs
Challenge: Develop a chatbot based on a fine-tuned model
(upbeat music) - [Instructor] In this fun hands-on challenge, you'll build a customer support Chatbot that uses the fine-tuned model to answer support questions about Keisha's Boutique. When building a Chatbot, you'll need to introduce a multiturn conversation. Until now, our conversations with ChatGPT have been single-turn. We send in a single prompt and get a single response back. This approach will not work with a Chatbot because we need ChatGPT to remember the conversation. We do that through writing code to manage a multiturn conversation. You'll need to keep track of the entire conversation history and send it to the model on each interaction to help it remember the conversation. Your first step for this hands-on challenge is to write functions that help you manage the conversation history so that it can be sent on each interaction with ChatGPT. Next, you'll set a system message that defines the persona of the AI assistant. Next, you'll send in user messages that contain…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
Contents
-
-
-
-
-
-
Train a new fine-tuned model4m 9s
-
(Locked)
Challenge: Fine-tune a pretrained LLM48s
-
(Locked)
Solution: Fine-tune a pretrained LLM3m 23s
-
(Locked)
Retrieve and use a fine-tuned model4m 3s
-
(Locked)
Challenge: Develop a chatbot based on a fine-tuned model1m 29s
-
(Locked)
Solution: Develop a chatbot based on a fine-tuned model4m 10s
-
-
-