近日，上海人工智能实验室携手商汤科技、香港中文大学和复旦大学，共同发布新一代大语言模型书生·浦语2.0。该版本的核心理念在于回归语言建模的本质，通过提升语料质量及信息密度，使模型基座的语言建模能力实现质的飞跃。
书生·浦语2.0具备强大的语言处理能力，支持200K token的上下文，可以一次性接收并处理约30万汉字的输入内容。在长文本中，它能准确提取关键信息，实现“大海捞针”的效果。这一突破性技术，将进一步推动人工智能在各个领域的应用。
书生·浦语2.0的发布，标志着我国在人工智能领域的研究取得了新的重要成果。作为一款开放源代码的大语言模型，它将为国内外研究人员提供一个高水平的研究平台，助力我国人工智能产业的快速发展。
英文翻译：
News Title: Shanghai AI Lab Releases Sheng·Puyu 2.0, Returning to the Essence of Language Modeling
Keywords: Artificial Intelligence, Large Language Model, Sheng·Puyu 2.0
News Content:
Recently, the Shanghai AI Lab, in collaboration with SenseTime, Chinese University of Hong Kong, and Fudan University, jointly released the new generation of large language model Sheng·Puyu 2.0. The core concept of Sheng·Puyu 2.0 lies in returning to the essence of language modeling, aiming to improve the quality of corpus and information density to achieve a qualitative leap in the language modeling capability of the model base.
Sheng·Puyu 2.0 boasts strong language processing capabilities, supporting 200K token context and able to receive and process approximately 300,000 Chinese characters at once. In long texts, it can accurately extract key information, achieving the effect of “fishing in a vast sea.” This groundbreaking technology will further promote the application of artificial intelligence in various fields.
The release of Sheng·Puyu 2.0 marks a new significant achievement in the research of artificial intelligence in our country. As an open-source large language model, it will provide a high-level research platform for domestic and international researchers, contributing to the rapid development of China’s artificial intelligence industry.
【来源】https://www.thepaper.cn/newsDetail_forward_26040295
Views: 1