Shulou(Shulou.com)11/24 Report--

Thank CTOnews.com netizens soft media Xinyou 2064893 for the clue delivery! CTOnews.com August 15 news, after Huawei Xiaoyi, Xiaomi Xiao Ai, OPPO Xiaobu assistant upgrade AI large model capabilities, vivo is also ready to make efforts in the field of large models.

At present, Huawei, Xiaomi, OPPO-related big models and new smart assistants have begun or are about to start testing, and now the cloud solution of vivo's self-developed model has also appeared on the C-Eval rankings, which may bring something different to Jovi assistants in OriginOS 4.

CTOnews.com Note: C-Eval is a comprehensive Chinese basic model evaluation suite. It contains 13948 multiple choice questions, covering four major directions: humanities, social sciences, science and technology, and other majors, including 52 different disciplines and four difficulty levels.

From the information given by C-Eval, vivo_Agent_LM_7B is a large-scale pre-training language model independently developed by vivo AI Global Research Institute. It is not difficult to see that it has 7 billion parameters from its naming.

Just looking at the final result, vivo_Agent_LM_7B finally scored 64.4, ranking fifth in C-Eval, very close to the second GPT-4, even stronger in the humanities, and doing well in the social sciences.

Related readings:

Lei Jun: Xiaomi set up a large model team in April, and the new version of Xiao Ai starts the invitation test today.

"OPPO Xiaobu Assistant will have the ability of AI large model, based on AndesGPT"

"AI big model empowers HarmonyOS 4 brand-new art, Huawei Yu Chengdong: adhere to AI assistance rather than AI replacement"

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.