Vivo will release its self-developed AI large model matrix C-Eval and CMMLU, ranking first in both lists

On October 16, the C-Eval large model evaluation list was updated. The list shows that vivo’s self-developed large model ranked first in the C-Eval global Chinese list. Previously, vivo's self-developed large models have achieved good results, ranking first in the C-Eval list of large models within 10 billion, first in the CMMLU global Chinese list, and first in its list of large models within 10 billion. The relevant person in charge of vivo revealed that vivo’s self-developed AI large models will be used for the first time in the upcoming OriginOS 4 system, including 5 self-developed large models with three different parameter levels: billion, tens of billions, and hundreds of billions. Comprehensive coverage of core application scenarios.

The C-Eval list is a comprehensive examination evaluation set for Chinese language models jointly constructed by Tsinghua University, Shanghai Jiao Tong University and the University of Edinburgh. It covers 52 different disciplines and has a total of 13,948 multiple-choice questions. It is currently the most comprehensive test evaluation set for Chinese language models. Authoritative Chinese AI large model evaluation list. The CMMLU data set is a comprehensive Chinese evaluation benchmark jointly launched by MBZUAI, Shanghai Jiao Tong University, and Microsoft Research Asia. It is extremely authoritative in evaluating the knowledge and reasoning capabilities of language models in the Chinese context.

This time, vivo's self-developed large AI model has simultaneously topped the C-Eval and CMMLU lists, demonstrating its absolute leading strength in the field of Chinese language models, and also reflecting the industry's support for vivo's AI innovation capabilities and development. Potential for sure.

At present, AI large model technology is developing rapidly, promoting disruptive changes in social production and lifestyle. In the mobile phone industry, it is also expected to become a key opportunity for manufacturers to accelerate product iteration and open up blue ocean tracks. This time vivo created a self-developed AI large model matrix and applied it to the new system, proving that its exploration of large models has advanced from the technology research and development stage to the application and industrial layout stage. This will not only effectively promote vivo's own business growth and The implementation of the high-end strategy will have a very positive driving effect on the entire industry.

It is understood that the new mobile operating system OriginOS 4 will be released at the vivo Developer Conference (2023 VDC) held on November 1. The system will launch vivo’s self-developed A large model to bring consumers more intelligence and Convenient and safe mobile phone use experience. The new functional experience brought by vivo’s self-developed large model and OriginOS 4, as well as more technology, service innovation and ecological construction achievements announced by vivo at the developer conference, are worth looking forward to and paying attention to.

Operator Finance (official WeChat public account yyscjrd) - a mainstream financial website, a website that comprehensively covers technology, finance, securities, automobiles, real estate, food, medicine, daily chemicals, wine and other consumer products .

The above is the detailed content of Vivo will release its self-developed AI large model matrix C-Eval and CMMLU, ranking first in both lists. For more information, please follow other related articles on the PHP Chinese website!