zhongshsh/MoExtend
ACL 2024 (SRW), Official Codebase of our Paper: "MoExtend: Tuning New Experts for Modality and Task Extension"
This project helps AI researchers and practitioners expand the capabilities of large language models (LLMs) to understand and process both text and image data. It takes an existing text-only LLM and integrates new 'experts' so it can handle visual information without costly retraining. The result is an LLM that can perform tasks requiring both language and vision, useful for those working on advanced AI applications.
No commits in the last 6 months.
Use this if you need to quickly adapt a pre-trained large language model to understand and integrate visual information, or extend its abilities to new multimodal tasks without starting from scratch.
Not ideal if you are looking for a pre-trained, ready-to-use multimodal model, as this project focuses on the framework for adapting existing models.
Stars
14
Forks
—
Language
Python
License
MIT
Category
Last pushed
Dec 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/zhongshsh/MoExtend"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
EfficientMoE/MoE-Infinity
PyTorch library for cost-effective, fast and easy serving of MoE models.
raymin0223/mixture_of_recursions
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation...
AviSoori1x/makeMoE
From scratch implementation of a sparse mixture of experts language model inspired by Andrej...
thu-nics/MoA
[CoLM'25] The official implementation of the paper
jaisidhsingh/pytorch-mixtures
One-stop solutions for Mixture of Expert modules in PyTorch.