Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Recent breakthroughs in natural language processing, comprehension, and generation have been greatly influenced by the development of large language models. This research presents a system that employs Ascend 910 AI processors and the MindSpore framework to train a language model exceeding one trillion parameters, specifically 1.085 trillion, referred to as PanGu-{\Sigma}. This model enhances the groundwork established by PanGu-{\alpha} by converting the conventional dense Transformer model into a sparse format through a method known as Random Routed Experts (RRE). Utilizing a substantial dataset of 329 billion tokens, the model was effectively trained using a strategy called Expert Computation and Storage Separation (ECSS), which resulted in a remarkable 6.3-fold improvement in training throughput through the use of heterogeneous computing. Through various experiments, it was found that PanGu-{\Sigma} achieves a new benchmark in zero-shot learning across multiple downstream tasks in Chinese NLP, showcasing its potential in advancing the field. This advancement signifies a major leap forward in the capabilities of language models, illustrating the impact of innovative training techniques and architectural modifications.
Description
TimesFM-3 represents an advanced time series foundation model that excels in highly precise multivariate forecasting with a single forward pass. This model, which consists of 330 million parameters, has undergone pre-training on a vast corpus of real-world and synthetic time series data, totaling over 1 trillion time points, thereby enhancing the effectiveness and zero-shot generalization capabilities seen in previous TimesFM iterations. It is adept at simultaneously predicting numerous coevolving time series and understanding dependencies that bolster accuracy without the need for task-specific fine-tuning. Furthermore, it accommodates multiple forecasting targets, including both point and quantile predictions, and incorporates past covariates that are only available historically, alongside dynamic covariates that pertain to future events such as planned promotions, holidays, or weather changes. Utilizing a decoder-only transformer architecture, TimesFM-3 processes sequential data in segments of 32 time steps, employing alternating causal temporal attention and full variate attention to integrate patterns across both time and interrelated series effectively. As a result, it provides a robust tool for forecasting complex time-dependent phenomena in various applications.
API Access
Has API
API Access
Has API
Screenshots View All
No images available
Integrations
PanGu Chat
Pricing Details
No price information available.
Free Trial
Free Version
Pricing Details
No price information available.
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
Huawei
Founded
1987
Country
China
Website
huawei.com
Vendor Details
Company Name
Founded
1998
Country
United States
Website
research.google/blog/timesfm-3-a-zero-shot-foundation-model-for-multivariate-forecasting/