Day 4 - Large Language Models

7-Day AI Research Training Workshop

Day 4 - Large Language Models I: Foundations and Fine-Tuning

Afternoon Session (2:00 PM - 6:00 PM)
2:00 - 3:00 PM	Evaluating Generative Models Analyze text generation outputs for coherence, factuality, and creativity.
3:00 - 4:00 PM	Instruction-Tuning Lab Prepare and merge Dolly15k, Alpaca, and FLAN datasets, then fine-tune GPT-2.
4:00 - 5:00 PM	Course on Prompt Engineering, Chain-of-Thought (CoT), and Hallucination Learn how to design robust prompts, manage reasoning chains, and mitigate false outputs.
5:00 - 6:00 PM	Q&A: Understanding the Human Side of LLMs