On June 14th local time, Nvidia released the Nemotron-4 340B (340 billion parameters) series model. According to Nvidia, developers can use this series of models to generate synthetic data for training large language models (LLMs) for commercial applications in industries such as medical care, finance, manufacturing, retail, and other industries. Nemotron-4 340B includes base model, Instruct model, and reward model. Nvidia used 9 trillion tokens (text units) for training. Nemotron-4 340B-Base can perform common sense reasoning tasks, such as ARC-c, MMLU, and BBH benchmark tests, comparable to Llama-3 70B, Mixtral 8x22B, and Qwen-2 72B models.
英伟达开源3400亿参数模型Nemotron-4 340B
Nvidia released the Nemotron-4 340B parameter model, which has an open source of 340 billion. According to Nvidia, developers can use this model to generate synthetic data for training large language models (LLMs) for commercial applications in industries
The translation is provided by third-party software.
The above content is for informational or educational purposes only and does not constitute any investment advice related to Futu. Although we strive to ensure the truthfulness, accuracy, and originality of all such content, we cannot guarantee it.