yuchenlin/LLM-Blender

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.

语言：Python · GitHub 星标：997 · Fork：91

话题：ensamble-methods · large-language-models · llm · natural-language-processing

在 GitHub 上查看原仓库