automix-llm/automix
Mixing Language Models with Self-Verification and Meta-Verification
This project helps developers and researchers integrate and optimize the use of different language models (LMs) to answer questions and solve tasks more reliably. You input a question and relevant context, and it uses smaller LMs for initial answers and verification. If the confidence is low, it automatically routes the query to a larger, more powerful LM, providing a more accurate final answer. This is for anyone building applications that rely on multiple LMs and want to improve output quality.
112 stars. No commits in the last 6 months.
Use this if you are building an application that needs to answer questions or generate text using language models, and you want to achieve higher accuracy by intelligently combining the strengths of both smaller and larger LMs.
Not ideal if you are a casual user looking for a ready-to-use chatbot or a simple API wrapper for a single language model.
Stars
112
Forks
10
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Dec 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/automix-llm/automix"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
genlm/genlm-control
Controlled text generation with programmable constraints
Intelligent-CAT-Lab/AlphaTrans
Artifact repository for the paper "AlphaTrans: A Neuro-Symbolic Compositional Approach for...
madaan/self-refine
LLMs can generate feedback on their work, use it to improve the output, and repeat this process...
PCI-ORG/PCI-Personnel
Policy Change Index for Personnel (PCI-Personnel)
gokmengokhan/deo-llm-reframing
Replication materials: Testing Distance-Engagement Oscillation as a prompting framework for...