AceGPT-v2-8B-Chat is an 8 billion parameter, fully fine-tuned generative text model developed by researchers from King Abdullah University of Science and Technology (KAUST), the Chinese University of Hong Kong, Shenzhen (CUHKSZ), and the Shenzhen Research Institute of Big Data (SRIBD). Optimized for dialogue applications, this model is particularly focused on the Arabic language domain, demonstrating superior performance compared to other open-source Arabic dialogue models in benchmark tests. It supports a context length of 8192 tokens and is designed for generating text outputs from text inputs.
Loading preview...
AceGPT-v2-8B-Chat Overview
AceGPT-v2-8B-Chat is an 8 billion parameter model from the AceGPT family, developed by a collaboration between King Abdullah University of Science and Technology (KAUST), the Chinese University of Hong Kong, Shenzhen (CUHKSZ), and the Shenzhen Research Institute of Big Data (SRIBD). This model is a fully fine-tuned generative text model specifically optimized for Arabic language dialogue applications.
Key Capabilities & Differentiators
- Arabic Language Specialization: Demonstrates superior performance compared to other open-source Arabic dialogue models in multiple benchmark tests.
- Comparable to Closed-Source Models: Achieves satisfaction levels comparable to some closed-source models like ChatGPT in Arabic language human evaluations.
- Benchmark Performance: The AceGPT-v2-8B-Chat model shows strong results across various Arabic and general benchmarks, including ArabicMMLU (62.21%), EXAMS (52.98%), and ACVA (76.54% clean).
- Dialogue Optimization: Designed as a chat-specific variant within the AceGPT family, which also includes base models.
Good For
- Developing Arabic-centric conversational AI applications.
- Tasks requiring high-quality text generation and understanding in the Arabic language.
- Researchers and developers focusing on Arabic NLP and LLM development.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.