Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,11 @@ pipeline_tag: time-series-forecasting
|
|
| 8 |
|
| 9 |
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
**Resources and Technical Documentation**:
|
| 12 |
* Paper: [A decoder-only foundation model for time-series forecasting](https://arxiv.org/abs/2310.10688), ICML 2024.
|
| 13 |
* [Google Research blog](https://research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting/)
|
|
|
|
| 8 |
|
| 9 |
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
|
| 10 |
|
| 11 |
+
# Updates
|
| 12 |
+
|
| 13 |
+
* October 2, 2025: We changed the structure of the model to fuse QKV matrices into one for speed optimization.
|
| 14 |
+
Please reinstall the latest version of the timesfm package to reflect these changes. Results should be unchanged.
|
| 15 |
+
|
| 16 |
**Resources and Technical Documentation**:
|
| 17 |
* Paper: [A decoder-only foundation model for time-series forecasting](https://arxiv.org/abs/2310.10688), ICML 2024.
|
| 18 |
* [Google Research blog](https://research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting/)
|