A New AI Research from China Introduces GLM-130B: A Bilingual (English and Chinese) Pre-Trained Language Model with 130B Parameters

In recent times, the zero-shot and few-shot capabilities of Large Language Models (LLMs) have increased significantly, with those with over 100B parameters giving state-of-the-art performance on various benchmarks. Such an advancement also presents a critical challenge with respect to LLMs, i.e., transparency. Very limited knowledge about these large-scale models and their training process is available […]

The post A New AI Research from China Introduces GLM-130B: A Bilingual (English and Chinese) Pre-Trained Language Model with 130B Parameters appeared first on …

advancement ai research ai shorts applications art artificial intelligence benchmarks bilingual capabilities challenge china chinese deep learning editors pick english few-shot giving language language model language models large language large language model large language models llms machine learning parameters performance research staff state tech news technology