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.

44
/ 100
Emerging

This project helps anyone working with large language models (LLMs) to get better results by combining the strengths of multiple models. You input a prompt and several different LLM responses, and it outputs a refined, higher-quality response. This is for AI practitioners, content creators, researchers, and developers who want to improve the outputs of open-source LLMs.

976 stars. No commits in the last 6 months.

Use this if you are using open-source large language models and want to consistently achieve superior performance by blending their best aspects into one high-quality output.

Not ideal if you are only working with a single LLM and are not interested in comparing or fusing multiple outputs.

large-language-models natural-language-generation AI-output-refinement content-optimization generative-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

976

Forks

88

Language

Python

License

Apache-2.0

Last pushed

Oct 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/yuchenlin/LLM-Blender"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.