User Intent Alignment Without Manual Annotation: Zephyr-7B Surpasses Llama2-Chat-70B
1. Team: HuggingFace H42. Paper Title: Zephyr: Direct Distillation of LM Alignment3. Paper Link:4. GitHub: https://github.com/huggingface/alignment-handbook Table of Contents: 1. Introduction2. Core Algorithms 2.1 Distilled Supervised Fine-Tuning (dSFT) 2.1.1 Traditional Methods 2.1.2 New Methods 2.1.3 Example Explanation (to aid understanding of the dSFT execution process) 2.2 AI Feedback through Preferences (AIF) 2.2.1 Traditional Methods 2.2.2 … Read more