EliotShen
/

qwen-3-4b-intervention

Model card Files Files and versions

GroupGPT

This repository contains the model weight of Qwen3-4b-Intervention as presented in GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant.

Downloads last month: 7

Safetensors

Model size

4B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for EliotShen/qwen-3-4b-intervention

GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant

Paper • 2603.01059 • Published Mar 1 • 1