MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic ApproximationJan 1, 2024·Lu Li,Tianyu Zhang,Zhiqi Bu,Suyuchen Wang,Huan He,Jie Fu,Yonghui Wu,Jiang Bian,Yong Chen,Yoshua Bengio· 0 min read Cite DOI URLTypeJournal articlePublicationCoRRLast updated on Nov 11, 2024 ← LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models Jan 1, 2024Resonance RoPE: Improving Context Length Generalization of Large Language Models Jan 1, 2024 →