How to Fine-Tune Open-Source LLMs Locally Using QLoRA!
In this video, I walk through a collab notebook in order to fine tune an open source LLM locally using QLoRA.
Here is my Twitter: / lukemoningtonai
Here is the Hugging Face collab notebook for QLoRA: https://colab.research.google.com/dri...
Feel free to post questions in the comments section!
0:00 Introduction
0:24 Explanation of Python Libraries
2:46 Loading the Model
5:18 Preparing the Model for Training
6:51 Preparing the Lora Configuration
8:45 Preparing the Dataset
9:24 Fine-Tuning the LLM
11:42 Saving the Model and Inferencing