Google Research has released TimesFM 3.0, a new time-series foundation model built on a Stacked Mixing Transformer architecture. This model is designed for time-series forecasting and utilizes a decoder-only approach. It has been pretrained on a variety of data sources, including Wikipedia pageviews and Google Trends, and features 20 transformer layers with a model dimension of 1280. AI
IMPACT This release provides a new foundation model for time-series forecasting, potentially improving accuracy and efficiency in applications relying on temporal data analysis.
RANK_REASON Release of a new foundation model for time-series forecasting with associated paper. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Trending Models →
- A decoder-only foundation model for time-series forecasting
- Google Research
- google/timesfm-3.0-pytorch
- Google Trends
- Stacked Mixing Transformer
- TimesFM
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →