Finetuning Llama 3.1 to talk like Rick Sanchez | Unsloth Tutorial

In this video, I'll show you how to make Llama 3.1 8B speak like Rick Sanchez. We'll start by creating a custom dataset from Rick and Morty transcripts in ShareGPT format. Then we'll finetune Llama with the Unsloth library inside a Lambda Labs instance (we need GPUs!). Finally, we'll convert and deploy the model to Ollama for local use. This is a fun way to learn about LLM finetuning while creating your own Rick-speaking AI assistant. So ... Wubba lubba dub dub! 🛸 –––––––––––––––––––––––––––––– GitHub 👉 https://github.com/neural-maze/rick-llm Unsloth 👉 https://unsloth.ai/ Ollama 👉 https://ollama.com/ Lambda 👉 https://lambdalabs.com/ –––––––––––––––––––––––––––––– If you like this content, you can also follow me here: 📩 Substack - https://theneuralmaze.substack.com/ 💼 LinkedIn - https://www.linkedin.com/in/migueloteropedrido 💻 GitHub - https://github.com/MichaelisTrofficus 🐦 Twitter - https://x.com/moteropedrido –––––––––––––––––––––––––––––– 0:00 Introduction 0:30 Project Overview 3:54 Repo Overview 5:48 Dataset Creation 12:12 Unsloth code 22:49 Lambda Labs 26:18 Launch GPU instance 27:12 Sync filesystems 29:38 SSH into the instance 32:38 Finetune 33:56 GGUF and Modelfile 35:40 Ollama Model 37:19 Chatting with Rick 39:00 Conclusion –––––––––––––––––––––––––––––– juicy fruit by Snoozy Beats / snoozybeats Creative Commons — Attribution 3.0 Unported — CC BY 3.0 Free Download / Stream: https://audiolibrary.com.co/snoozybea... Music promoted by Audio Library • juicy fruit – Snoozy Beats (No Copyri... ––––––––––––––––––––––––––––––