From Research to Production: Fine-Tuning and Aligning LLMs

Explore the crucial steps for transitioning Large Language Models (LLMs) from research to production environments, focusing on effective fine-tuning and alignment techniques. Learn how to fine-tune and evaluate LLMs using Supervised Fine-Tuning (SFT) and advanced methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO). Gain insights into practical applications for aligning LLMs with production goals, presented by Philipp Schmid, Technical Lead at Hugging Face. Discover strategies to democratize good machine learning through open source and open science, and understand how to productionize cutting-edge and generative AI models effectively.

From Research to Production: Fine-Tuning & Aligning LLMs // Philipp Schmid // AI in Production