Fine-tune a Small LLM on Custom Data

Prepare an instruction-tuning dataset, fine-tune Phi-2 or Mistral 7B using LoRA/QLoRA on free Colab TPUs, and rigorously evaluate the fine-tuned model vs. the base.

You will learn to:

• Curate and format a high-quality instruction-tuning dataset in JSONL format
• Understand LoRA and QLoRA — how parameter-efficient fine-tuning works
• Fine-tune a small open-source LLM (Phi-2 or Mistral 7B) on Google Colab for free
• Evaluate a fine-tuned model rigorously against its base model using an LLM judge
• Document model training choices, dataset statistics, and evaluation results professionally