| library_name: rushd | |
| license: apache-2.0 | |
| language: | |
| - ar | |
| - en | |
| tags: | |
| - rushd | |
| - moe | |
| - arabic-nlp | |
| - early-exit | |
| - mixture-of-experts | |
| pipeline_tag: text-generation | |
| base_model: Qwen/Qwen3.5-27B | |
| # Rushd-Agent | |
| An efficient MoE-based agentic system with NCI-driven early exit for Arabic natural language understanding. | |
| ## Architecture | |
| - **Router**: Qwen2.5-7B with quantile-balanced expert selection | |
| - **Experts**: 6 domain-specialized Qwen3.5 models (Geo 27B + Writer/Game/Decision/Plan/Logic 9B) | |
| - **Early Exit**: Noema Predictor (21M params, 98.3% accuracy, 3.8x speedup) | |
| - **API**: OpenAI-compatible server on port 8777 | |
| ## Paper | |
| See `rushd_agent_paper.pdf` for full details. | |
| ## Citation | |
| ```bibtex | |
| @misc{yahya2025rushd, | |
| title={Rushd-Agent}: An Efficient MoE-Based Agentic System with NCI-Driven Early Exit, | |
| author={Yahya}, | |
| year={2025}, | |
| publisher={Hugging Face} | |
| } | |
| ``` | |