Jais 2: A Family of Arabic-Centric Open Large Language Models
Jais 2: A Family of Arabic-Centric Open Large Language Models
Jais 2：以阿拉伯语为核心的开源大语言模型系列
Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report.
摘要： Jais 2 是由 MBZUAI（穆罕默德·本·扎耶德人工智能大学）、Cerebras 和 Inception 联合开发的一系列以阿拉伯语为核心的大语言模型。该系列旨在推动阿拉伯语语言建模的发展，并在本报告评估的阿拉伯语及文化基础基准测试中表现出色。
The family includes, to our knowledge, the largest open Arabic-centric LLM trained from scratch at 70B parameters, and a competitive 8B-parameter variant among the evaluated open models. A custom Arabic-centric vocabulary enables efficient training and inference. In addition, an optimized architecture and training recipe yield highly compute-efficient training.
据我们所知，该系列包括目前最大的从零训练的开源阿拉伯语大语言模型（70B 参数），以及在同类评估开源模型中极具竞争力的 8B 参数版本。定制的阿拉伯语词表实现了高效的训练与推理。此外，优化的架构和训练方案带来了极高的计算训练效率。
With a substantially smaller token budget than comparable models, Jais 2 achieves strong Arabic performance on the benchmarks considered in this report and competitive English results. The models obtain leading results among the evaluated open models on OALL2 and AraGen. They also perform strongly on several culturally grounded Arabic benchmarks, including poetry, religion, cuisine, and dream interpretation, as well as in general tasks such as translation and summarization.
相比同类模型，Jais 2 在显著较小的 Token 预算下，在本报告所考虑的基准测试中实现了强大的阿拉伯语性能，并取得了具有竞争力的英语表现。这些模型在 OALL2 和 AraGen 的评估中，在同类开源模型中处于领先地位。它们在多个基于阿拉伯文化的基准测试中也表现强劲，涵盖诗歌、宗教、烹饪和解梦等领域，并在翻译和摘要等通用任务中表现优异。
We release the models in HuggingFace under a commercially permissive license. Jais 2 70B is also released as a chat app on the Web, iOS, and Android; it runs on Cerebras hardware, delivering up to 2,000 tokens per second, and enabling high-throughput Arabic-centric chat serving in our deployment setting.
我们已在 HuggingFace 上以商业许可协议发布了这些模型。Jais 2 70B 还以聊天应用的形式在 Web、iOS 和 Android 平台上发布；它运行在 Cerebras 硬件上，每秒可生成高达 2,000 个 Token，并在我们的部署环境中实现了高吞吐量的阿拉伯语聊天服务。
By uniting scale, linguistic diversity, cultural fidelity, openness, and speed, Jais 2 provides an open-weight foundation intended to support further research and development in Arabic-centric LLMs.
通过结合规模化、语言多样性、文化忠实度、开放性和速度，Jais 2 提供了一个开放权重的基石，旨在支持以阿拉伯语为核心的大语言模型的进一步研究与开发。