Home / Open-source AI / LLM-Blender
LLM-Blender
by yuchenlin
[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.
GitHub stars999
Forks91
7d change–
LanguagePython
LicenseApache-2.0
Last commit22 Oct 2024