TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Python
push poetry version
Rajat Sen4aec27ee0265
diff --git a/.github/workflows/main.yml b/.github/workflows/main.ymlindex 9c92025..df17594 100644--- a/.github/workflows/main.yml+++ b/.github/workflows/main.yml@@ -23,7 +23,7 @@ jobs:# e.g. poetry version 0.1.${{ github.run_number }}- name: Set Version numberrun: |- poetry version 1.2.5+ poetry version 1.2.6- name: Build and Publish to PyPIrun: |poetry config pypi-token.pypi ${{ secrets.PYPI_API_TOKEN }}diff --git a/README.md b/README.mdindex ef260c3..b8c1e49 100644--- a/README.md+++ b/README.md@@ -23,19 +23,17 @@ We recommend at least 32GB RAM to load TimesFM dependencies.## Checkpoint timesfm-1.0-200m (-pytorch)-timesfm-1.0-200m is the first open model checkpoint:+timesfm-1.0-200m is our first open model checkpoint:- It performs univariate time series forecasting for context lengths up to 512 timepoints and any horizon lengths, with an optional frequency indicator.- It focuses on point forecasts, and does not support probabilistic forecasts. We experimentally offer quantile heads but they have not been calibrated after pretraining.-- It requires the context to be contiguous (i.e. no "holes"), and the context and the horizon to be of the same frequency.## Checkpoint timesfm-2.0-500m (-jax/-pytorch)-timesfm-2.0-500m is the second open model checkpoint:+timesfm-2.0-500m is our second open model checkpoint:- It performs univariate time series forecasting for context lengths up to 2048 timepoints and any horizon lengths, with an optional frequency indicator.- It focuses on point forecasts. We experimentally offer 10 quantile heads but they have not been calibrated after pretraining.-- It requires the context to be contiguous (i.e. no "holes"), and the context and the horizon to be of the same frequency.## Benchmarks