【上海AI实验室与多方联合发布书生·浦语2.0，开启大语言模型新篇章】
上海人工智能实验室携手商汤科技，以及香港中文大学和复旦大学的专家学者，近日共同推出了新一代大语言模型——书生·浦语2.0，并宣布该模型正式开源。这一举措标志着人工智能领域的语言建模技术迈向了新的高度，旨在回归语言建模的核心本质，以提升模型的语料质量和信息密度。
书生·浦语2.0的设计理念独特，它强调通过优化语料库，增强信息的密集程度，从而实现语言建模能力的显著提升。这一模型的一大亮点在于其强大的处理能力，支持高达200K token的上下文，能一次性接收并处理约30万个汉字的输入内容。这一特性使得书生·浦语2.0在处理长文本时游刃有余，能够精准地提取关键信息，即便在海量文本中也能实现“大海捞针”般的高效信息提取。
这一创新性的开源项目不仅将推动中国在人工智能领域的研究与发展，同时也为全球科研人员提供了新的工具和平台，共同探索语言建模的无限可能。书生·浦语2.0的发布，无疑将对自然语言处理技术的广泛应用产生深远影响，包括但不限于智能客服、文本理解和机器翻译等领域。
来源：澎湃新闻
英语如下：
**News Title:** “Shanghai AI Lab Collaborates with Multiple Parties to Open Source Scholar·Puyu 2.0: Rethinking Language Modeling for Precise Long Text Information Extraction”
**Keywords:** Puyu 2.0 Open Source, AI Language Model, Multischool Cooperation
**News Content:**
The Shanghai AI Laboratory, in conjunction with SenseTime, as well as experts from the Chinese University of Hong Kong and Fudan University, recently jointly launched the new generation large language model, Scholar·Puyu 2.0, and announced that the model is now open source. This move signifies a new milestone in language modeling technology within the field of artificial intelligence, aiming to回归the core essence of language modeling to enhance the quality and density of the model’s linguistic data.
Scholar·Puyu 2.0 boasts a distinctive design philosophy, emphasizing the optimization of the corpus to increase information density, thereby significantly improving language modeling capabilities. A key feature of this model is its powerful processing ability, supporting up to 200K tokens of context, allowing it to handle and process approximately 300,000 Chinese characters in one go. This characteristic enables Scholar·Puyu 2.0 to handle long texts effortlessly, precisely extracting crucial information even from vast amounts of text, akin to efficiently extracting needles from a haystack.
This innovative open-source project will not only propel China’s research and development in artificial intelligence but also provide a new tool and platform for global researchers to explore the endless possibilities of language modeling. The launch of Scholar·Puyu 2.0 is set to have a profound impact on the widespread application of natural language processing technology, including but not limited to intelligent customer service, text understanding, and machine translation.
**Source:** Phoenix News
【来源】https://www.thepaper.cn/newsDetail_forward_26040295
Views: 1