Huawei PanGu

Edit links
From Wikipedia, the free encyclopedia

Huawei PanGu
Developer(s)Huawei
Initial release3.0, July 7, 2023; 10 months ago (2023-07-07)
Stable release
3.0 / July 7, 2023; 10 months ago (2023-07-07)
Available inChinese, English, Russian
TypeLarge language model
LicenseProprietary

Huawei PanGu, PanGu, PanGu-Σ or PanGu-π (Chinese: 盘古大模型; pinyin: pángǔ dà móxíng) is a multimodal large language model developed by Huawei. It was announced on July 7, 2023, positioned as a contender to other multimodal large language models.[1]

The name of the large learning language model, PanGu, was derived from the Chinese mythology and folklore of Pangu, a primordial character related to the creation of the world.[2]

History[edit]

Early Development[edit]

In April 2023, Huawei released a paper detailing the development of PanGu-Σ, a colossal language model featuring 1.085 trillion parameters. Developed within Huawei's MindSpore 5 framework, PanGu-Σ underwent training for over 100 days on a cluster system equipped with 512 Ascend 910 AI accelerator chips, processing 329 billion tokens in more than 40 natural and programming languages.[3]

PanGu-Σ incorporates Random Routed Experts (RRE) and the Transformer decoder architecture, allowing easy extraction of sub-models for various applications like conversation, translation, code production, and natural language interpretation. The model achieves 6.3 times faster training throughput compared to MoE models with the same hyper-parameters. In the Chinese domain, it outperforms previous state-of-the-art models across 16 tasks in a zero-shot setting. Trained on datasets from 40 domains, including Chinese, English, Bilingual, and code, PanGu-Σ excels in few-shot natural-language understanding, open-domain discussion, question answering, machine translation, and code creation.[4][5]

Launch[edit]

During the Huawei Developer Conference on July 7, 2023, Huawei introduced PanGu 3.0, a large language model (LLM), tailored for sectors like government, finance, manufacturing, mining, and meteorology utilizing Huawei Cloud solutions. In the subsequent month, Huawei launched the Celia Virtual Assistant with advanced AI features, capable of generating long text replies based on user voice commands and set to release with HarmonyOS 4.0 for eligible devices.[6][7]

The LLM was designed for enterprises seeking advantages in the AI industry, focusing on task execution over creative work, unlike traditional models used for general purposes like chatbots, poetry, and visual content creation.[8]

Using the same technology as ChatGPT, Huawei's LLM features a hierarchical architecture, allowing customers to adapt the model to various tasks and train it on their own datasets, making it versatile across various industries.[9]

Updates[edit]

On August 5, 2023, Huawei partnered with ECMWF on the AI model to launch the global weather forecasting that takes advantage of Huawei Cloud solutions, with Pangu-Weather Model with MindSpore on top, that is available to access on the website of the European Centre for Medium-Range Weather Forecasts (ECMWF) that aims to provide accurate weather data.[10][11]

On December 19, 2023, Huawei Cloud announced it's financial services on its Pangu powered AI Finance platform in the global market. The tech giant introduced the product at its 2023 Huawei Cloud Fintech Summit as an aim to reshape the digital finance industries with efficient characteristics, to boost Fintech firms in the global market. It incorporates a variety of advanced features and technologies using AI, huge data analytics, and blockchain.[12]

On January 18, 2024, Huawei revealed the replaced base operating system, HarmonyOS NEXT of HarmonyOS alongside OpenHarmony and Oniro OS that includes the Pangu AI model, MindSpore AI Framework for Internet of things of smart devices, smart wearables, personal computing devices, mobile devices and auto industries with self driving technologies for various hardware types that take advantage of HiSilicon NPU-enabled chips.[13]

Technical specifications[edit]

Pangu Large Model 3.0 built for industry is structured with a 5+N+X three-tier structure. The first layer – L0 is Pangu's five basic large models to provide a variety of skills to meet industry scenarios, such as Natural language large models, Visual large models, Multimodal large models, Prediction large models and Scientific computing large models. The second layer – L1 is N large industry models. With this, it provides industry-wide large models that are trained using industry public data, including government affairs, finance, manufacturing, mining, weather, and more. It also uses industry customers’ own data on Pingu's L0 and L1, it trains its own proprietary large models for customers. And the last third layer, the L2 layer, gives customers more detailed scenario models. It's more focused on a specific application scenario or specific business and delivers customers with out-of-the-box model services.[14]

See also[edit]

References[edit]

  1. ^ "Reshaping Industries with AI: Huawei Cloud launches Pangu Models 3.0 and Ascend AI Cloud services". CITI Newsroom. CITI Newsroom. Retrieved February 13, 2024.
  2. ^ Nair, Arya M. (July 8, 2023). "Huawei rolls out latest version of its deep learning AI model, Pangu - GCC Business News". Retrieved May 29, 2024.
  3. ^ Upadhyay, Shyam Nandan. "Huawei Researchers Develop LLM With 1.085 Trillion Parameters". AnalyticsIndiaMag. AnalyticsIndiaMag. Retrieved February 13, 2024.
  4. ^ "Huawei Researchers Unveil Pangu-Σ: Trillion-Parameter Language Model with Sparse Architecture". Multiplatform.ai. Multiplatform.ai. Retrieved February 13, 2024.
  5. ^ Tickoo, Aneesh. "Huawei Researchers Develop Pangu-Σ: A Large Language Model With Sparse Architecture And 1.085 Trillion Parameters". marktechpost.com. marktechpost.com. Retrieved February 13, 2024.
  6. ^ "Huawei Pangu AI models for Government, finance, manufacturing, mining, meteorology". HC Newsroom. HC Newsroom. Retrieved February 13, 2024.
  7. ^ Sarkar, Amy. "Huawei launches Voice Assistant with large Pangu AI model". HC Newsroom. HC Newsroom. Retrieved February 13, 2024.
  8. ^ "Revolutionizing Global AI Landscape: Huawei's PanGu Megamodel Set to Transform Industries Worldwide". LinkedIn. Grosso Link Sàrl. Retrieved February 13, 2024.
  9. ^ Jarrett, Miranda. "Huawei to revolutionise applications of AI with new Pangu model". Dao Insights. Dao Insights. Retrieved February 13, 2024.
  10. ^ Li, Deng. "Huawei Pangu-Weather Model debuts European ECMWF website". HC Newsroom. HC Newsroom. Retrieved February 13, 2024.
  11. ^ Mishra, Yash. "Huawei Cloud will build large-scale high-precision regional weather forecast Pangu model". HC Newsroom. HC Newsroom. Retrieved February 13, 2024.
  12. ^ Birch, Scott. "Huawei Cloud and Pangu AI model reshaping finance industry". FinTech Magazine. FinTech Magazine. Retrieved February 13, 2024.
  13. ^ CHUNG, JACKSON. "Huawei HarmonyOS NEXT 'Galaxy Edition' Previewed in New Video, Leaves Android Behind". TECHEBLOG. TECHEBLOG. Retrieved February 13, 2024.
  14. ^ "Huawei launches latest AI model, Pangu 3.0". Business Today (Malaysia). Business Today (Malaysia). Retrieved February 13, 2024.


Retrieved from "https://en.wikipedia.org/w/index.php?title=Huawei_PanGu&oldid=1226195193"