上海人工智能实验室与商汤科技联合香港中文大学和复旦大学正式发布新一代大语言模型书生·浦语2.0，并正式开源。这一版本的核心理念在于回归语言建模的本质，致力于通过提高语料质量及信息密度，实现模型基座语言建模能力获得质的提升。
书生·浦语2.0支持200K token的上下文，一次性接收并处理约30万汉字的输入内容，准确提取关键信息，实现长文本中“大海捞针”。这一功能对于处理大量的中文文本信息，具有重要的实际应用价值。
此次发布的书生·浦语2.0不仅是一个大型的语言模型，更是人工智能领域的一次重要突破。它的开源将极大地推动人工智能领域的研究和发展，同时也为广大的开发者提供了强大的语言处理工具。
英文标题Title：Shanghai AI Lab Releases Sheng·Puyu 2.0 Open Source
英文关键词Keywords：AI Lab, Sheng·Puyu 2.0, Open Source
News content:
The Shanghai Artificial Intelligence Laboratory, in collaboration with SenseTime Technology, Hong Kong Chinese University, and Fudan University, has officially released the new generation of large-scale language model Sheng·Puyu 2.0 and made it open source. The core concept of this version is to return to the essence of language modeling, committed to improving the quality of corpus and information density, achieving a qualitative leap in the language modeling capability of the model base.
Sheng·Puyu 2.0 supports 200K token contexts and can process about 300,000 Chinese characters of input content at once, accurately extracting key information and realizing “fishing a needle in a haystack” in long texts. This function has important practical application value for handling a large amount of Chinese text information.
This release of Sheng·Puyu 2.0 is not only a large-scale language model but also an important breakthrough in the field of artificial intelligence. Its open source will greatly promote the research and development in the field of artificial intelligence and also provide a powerful language processing tool for a wide range of developers.
【来源】https://www.thepaper.cn/newsDetail_forward_26040295
Views: 1