SenseTime and Shanghai AI Lab released "Shu Sheng - Pu Language" large model...

Sheng - Pu Language large model

DIYuan | 2023-06-07 18:00

【數(shù)據(jù)猿導(dǎo)讀】 SenseTime and Shanghai AI Lab released "Shu Sheng - Pu Language" large model

On June 7, the official microblogging site of SenseTime showed that SenseTimeand Shanghai AI Lab, together with Chinese University of Hong Kong, Fudan University and Shanghai Jiao Tong University, recently released the 100-billion-parameter large language model "Shusheng-Pu Language" (InternLM). With 104 billion parameters, "Shusheng-PuLanguage" is trained on a multilingual high-quality dataset containing 1.6 trillion tokens. The comprehensive evaluation results show that "Shusheng-Puranyu" not only excels in multiple test tasks such as knowledge mastery, reading comprehension, mathematical reasoning, and multilingual translation, but also has strong comprehensive ability, thus excelling in comprehensive exams and outperforming ChatGPT in many Chinese exams, including Data sets for various subjects in the Chinese college entrance exams.

來(lái)源：DIYuan

收藏分享

聲明：數(shù)據(jù)猿尊重媒體行業(yè)規(guī)范，相關(guān)內(nèi)容都會(huì)注明來(lái)源與作者；轉(zhuǎn)載我們?cè)瓌?chuàng)內(nèi)容時(shí)，也請(qǐng)務(wù)必注明“來(lái)源：數(shù)據(jù)猿”與作者名稱(chēng)，否則將會(huì)受到數(shù)據(jù)猿追責(zé)。