Module 5: Custom LLMs and Fine-Tuning
Type: Advanced technical session in collaboration with Research Computing & Emerging Technologies
Location: LGRC A112 + Zoom
Date: December 2nd, 12:00 – 2:00 PM
Learn how to build, fine-tune, and deploy custom AI models using UMass Amherst’s Unity Research Computing Platform’s infrastructure, including:
- Accessing multi-GPU resources for training
- Fine-tuning on domain-specific corpora
- Evaluating model performance and deploying privately
SELF-PACED RESOURCES
These optional materials are provided for participants who would like additional enrichment. You can explore them at your own pace to deepen your understanding and get more out of the workshop experience.
1. Finetuning Large Language Models
2. Github – huggingface / smol-course
3. How to fine-tune open LLMs in 2025 with Hugging Face
4. Fine-tuning LLMs Guide
5. Unity Research Computing Platform