Huawei has officially launched the openPangu 2.0 Pro model alongside its technical report. The company has announced that interested users can easily download the new model solution and use it accordingly without any kind of interruptions.
openPangu 2.0 Pro is a massive open-weight Mixture-of-Experts (MoE) large language model featuring approximately 505 billion total parameters with 18 billion active per token and a 512K context window.
The company has launched Huawei openPangu 2.0 Pro as an open-source AI model brand. It can offer best practice references for the industry to make good use of Ascend chipsets in terms of training and inference technology.
On the greener side, it can help to build a powerful intelligent foundation for the Agent era, and accelerate the commercial innovation and ecosystem prosperity of artificial intelligence.
The Chinese tech giant has mentioned the exact components and internal parameters of the openPangu 2.0 Pro on the open-source platforms. Users can visit the particular platform and download the large language model for their use.
Huawei said:
“We sincerely invite global developers, enterprise partners, and researchers to download and use them, or visit the Huawei Cloud MaaS Model-as-a-Service platform for an online experience. We welcome user feedback to help the open-source ecosystem continue to improve.”
(Image Credits: Huawei Blog)
