deep-diver/llamaduo
[ACL'25] Official Code for LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs
Seamlessly transfer the intelligence of large, cloud-based AI models like GPT-4o or Claude 3 to smaller, local models such as Gemma or Llama 3. This process involves using the cloud model to generate synthetic data, which then trains the local model, ensuring it can perform specific tasks just as well. This tool is ideal for machine learning engineers or MLOps practitioners who manage AI deployments.
317 stars. No commits in the last 6 months.
Use this if you need to migrate an existing AI application from a cloud-based LLM to a smaller, on-premise model due to privacy concerns, offline requirements, operational failures, or to maintain consistent model behavior across versions.
Not ideal if you are developing a new AI application from scratch and do not have an existing cloud LLM serving as a 'teacher' model for knowledge transfer.
Stars
317
Forks
30
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/deep-diver/llamaduo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NX-AI/xlstm
Official repository of the xLSTM.
sinanuozdemir/oreilly-hands-on-gpt-llm
Mastering the Art of Scalable and Efficient AI Model Deployment
DashyDashOrg/pandas-llm
Pandas-LLM
wxhcore/bumblecore
An LLM training framework built from the ground up, featuring a custom BumbleBee architecture...
MiniMax-AI/MiniMax-01
The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model &...