hugpadhugpad

TsinghuaC3I / ZEDA-GLM-4.7-Flash-Dynamic

Text Generation30B262Updated May 21, 2026
Hugging Face

Downloads

26

Likes

2

Last updated

May 21, 2026

License

mit

This repository contains the dynamic Mixture-of-Experts (MoE) model based on GLM-4.7-Flash, transformed using the Zero-Expert Self-Distillation Adaptation (ZEDA) framework.

Tasks & library

  • text generation

Tags

  • glm4_moe_lite_plus_plus
  • text-generation
  • conversational

Technical specifications

Parameters30B
LibraryNot available
LanguagesNot available
Base modelzai-org/GLM-4.7-Flash
Licensemit