Completed
Fine-tuning with LoRA
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Fine-tuning Llama 2 for Tone or Style Using Shakespeare Dataset
Automatically move to the next video in the Classroom when playback concludes
- 1 How to fine tune on a custom dataset
- 2 What dataset should I use for fine-tuning?
- 3 Fine-tuning in Google Colab
- 4 Loading Llama 2 with bitsandbytes
- 5 Fine-tuning with LoRA
- 6 Target modules for fine-tuning
- 7 Loading data for fine-tuning
- 8 Training Llama 2 with a validation set
- 9 Setting training parameters for fine-tuning
- 10 Choosing batch size for training
- 11 Setting gradient accumulation for training
- 12 Using an eval dataset for training
- 13 Setting warm-up parameters for training
- 14 Using AdamW for optimisation
- 15 Fix for when commands don't work in Colab
- 16 Evaluating training loss
- 17 Running inference after training
