Prismadic/magnet
the small distributed language model toolkit; fine-tune state-of-the-art LLMs anywhere, rapidly
This toolkit helps machine learning engineers and researchers quickly adapt cutting-edge large language models (LLMs) to specific tasks and data, even with limited hardware. You provide your specialized text data and the desired LLM, and it outputs a fine-tuned, more accurate language model tailored to your needs. This is perfect for teams needing to deploy custom LLMs without massive cloud infrastructure.
No commits in the last 6 months.
Use this if you need to fine-tune state-of-the-art large language models efficiently across various hardware setups, from personal computers to distributed clusters, for specialized applications.
Not ideal if you are looking for a pre-trained, off-the-shelf language model that requires no customization or specific domain adaptation.
Stars
32
Forks
4
Language
Python
License
MIT
Category
Last pushed
Oct 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Prismadic/magnet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lfnovo/esperanto
A unified interface for various AI model providers
apocas/restai
RESTai is an AIaaS (AI as a Service) open-source platform. Built on top of LlamaIndex &...
baidubce/bce-qianfan-sdk
Provide best practices for LMOps, as well as elegant and convenient access to the features of...
sbhjt-gr/InferrLM
On-device AI for iOS & Android
ProviderProtocol/ai
0-DEP AI DX SDK