Fine-tuning LLM with QLoRA on Single GPU: Training Falcon-7b on ChatBot Support FAQ Dataset

Venelin Valkov
Fine-tuning LLM with QLoRA on Single GPU: Training Falcon-7b on ChatBot Support FAQ Dataset
  • 1 hours
  • Beginner
  • Free
  • Online
In this video, you'll learn how to of fine-tuning the Falcon 7b LLM (40b version is #1 on the Open LLM Leaderboard) on a custom dataset using QLoRA. The Falcon model is free for research and commercial use. We'll use a dataset consisting of Chatbot customer support FAQs from an ecommerce website.

Throughout the video, we'll cover the steps of loading the model, implementing a LoRA adapter, and conducting the fine-tuning process. We'll also monitor the training progress using TensorBoard. To conclude, we'll compare the performance of the untrained and trained models by evaluating their responses to various prompts. Discord: https://discord.gg/UaNPxVD6tv Prepare for the Machine Learning interview: https://mlexpert.io Subscribe: http://bit.ly/venelin-subscribe Falcon LLM: https://falconllm.tii.ae/ HuggingFace Open LLM Leaderboard: https://huggingface.co/spaces/Hugging... 00:00 - Introduction 01:08 - Text Tutorial on MLExpert.io 01:43 - Falcon LLM 04:18 - Google Colab Setup 05:32 - Dataset 08:15 - Load Falcon 7b and QLoRA Adapter 12:20 - Try the Model Before Training 14:40 - HuggingFace Dataset 15:58 - Training 20:38 - Save the Trained Model 21:34 - Load the Trained Model 23:19 - Evaluation 28:53 - Conclusion

Sign up Course