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.
PythonApache-2.0
Stargazers
- 0xDing@pleisto
- abhishekbediTentronix NZ
- alechenningerRed Hat
- bingzhengwei
- DungNasSa10VinAI Research
- endymecy@tencent
- fly51flyPRIS
- GanjinZeroDAMO Academy
- heblade
- HuangOwenVSDL Lab, HKUST
- huliangbing
- iiLaurens
- indiejosephSoft Butter Studio
- inimahIndonesian Institute of Sciences (LIPI)
- jabogithub
- jdf-progUniversity of Waterloo
- JeffCarpenterCanada
- MichelML@valence-labs
- mingfangNew York
- MoomoocowPlus
- peterjc123Shanghai, China
- SandalotsVolcanak
- shaunstoltz
- SihengLi99Tencent
- SushantDaga
- taku-itoLangsmith Inc. / Tohoku NLP Lab
- TianqiYe
- tokestermwCresta
- unverciftciMath & AI Institute
- wang-debug
- wzhouadZoom
- YaoMarkMuHong Kong
- yuchenlin@allenai
- yusahmed4321
- yusuf-jkhan1California
- ZessayAlibaba Group