Shortened LLaMA: A Simple Depth Pruning for Large Language Models Paper • 2402.02834 • Published Feb 5 • 14
view article Article Preference Tuning LLMs with Direct Preference Optimization Methods Jan 18 • 35
Preference Datasets for DPO Collection This collection contains a list of curated preference datasets for DPO fine-tuning for intent alignment of LLMs • 7 items • Updated Jul 30 • 29
view article Article Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA May 24, 2023 • 90