DPO/ORPO Datasets Collection List of binarized general preference datasets suitable for DPO and ORPO finetuning with HF Alignment Handbook. • 12 items • Updated 14 days ago • 1
Llama 3 Merges Collection Here is a collection of merged models based on Llama-3 variants to showcase the seamless compatibility of MergeKit with Llama-3 architecture. • 6 items • Updated 14 days ago • 2
Arcee's MergeKit: A Toolkit for Merging Large Language Models Paper • 2403.13257 • Published Mar 20 • 17
Model Merging Collection Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 29 items • Updated 1 day ago • 181