avnlp/llm-blender

LLM-Blender: Ensembling framework that maximizes LLM performance via pairwise ranking. Employs PairRanker to rank candidates and GenFuser to merge outputs, generating superior responses by combining the diverse strengths of multiple open-source models.

37
/ 100
Emerging

This tool helps you get higher quality, more reliable text responses from large language models (LLMs) when generating content. It takes the same input prompt and sends it to several LLMs, then ranks their individual responses and intelligently merges the best parts into a single, superior final output. It is designed for developers building applications that rely on LLM-generated text, such as chatbots or content creation tools.

Use this if you are building an application with multiple LLMs and need a way to consistently improve the quality and coherence of their combined text outputs.

Not ideal if you are a casual LLM user looking for a simple, out-of-the-box solution without any programming, or if you only use a single LLM for your tasks.

AI-application-development natural-language-generation LLM-orchestration text-summarization question-answering
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

36

Forks

3

Language

Python

License

MIT

Last pushed

Dec 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/avnlp/llm-blender"

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