release: v0.1.3

docs/changelogs/index.md

@@ -0,0 +1,6 @@
+# Changelog
+
+Welcome to the FoundationForecast Changelog. Here you will find a list of changes, updates, and improvements for each release. Explore the details of each version below.
+
+- [v0.1.3](v0.1.3.md)
+- [v0.1.2](v0.1.2.md)

docs/changelogs/v0.1.2.md

@@ -0,0 +1,26 @@
+### Features
+
+* **Tafsut foundation model**: Added support for [Tafsut](https://github.com/Tafsut-FM/tafsut), a zero-shot probabilistic univariate time series foundation model. Use it via the `Tafsut` class with checkpoint `Tafsut-FM/tafsut-univariate-base`.
+
+    ```python
+    import pandas as pd
+    from foundationforecast import Tafsut
+
+    df = pd.read_csv(
+        "https://timecopilot.s3.amazonaws.com/public/data/air_passengers.csv",
+        parse_dates=["ds"],
+    )
+
+    model = Tafsut()
+    fcst_df = model.forecast(df, h=12)
+    ```
+
+* **GIFT-Eval replication experiment**: Added the `experiments/gift-eval` benchmark harness with Modal CI integration and Hugging Face leaderboard verification against published reference results.
+
+### Fixes
+
+* Improved quantile sorting, device handling, and model routing across foundation model backends.
+
+---
+
+**Full Changelog**: https://github.com/TimeCopilot/foundationforecast/compare/v0.1.1...v0.1.2

docs/changelogs/v0.1.3.md

@@ -0,0 +1,38 @@
+### Features
+
+* **TimesFM 3.0 foundation model**: Added support for [`google/timesfm-3.0-pytorch`](https://huggingface.co/google/timesfm-3.0-pytorch) via a new `_TimesFMV3` backend powered by `TimesFM3Evaluator` and `ModelConfig` from [`timecopilot-timesfm>=0.4.0`](https://pypi.org/project/timecopilot-timesfm/). The wrapper treats each series independently (univariate panel mode), matching the existing TimesFM 2.5 integration pattern.
+
+    ```python
+    import pandas as pd
+    from foundationforecast import TimesFM
+
+    df = pd.read_csv(
+        "https://timecopilot.s3.amazonaws.com/public/data/air_passengers.csv",
+        parse_dates=["ds"],
+    )
+
+    model = TimesFM(
+        repo_id="google/timesfm-3.0-pytorch",
+        alias="TimesFM-3",
+        context_length=2048,
+    )
+    fcst_df = model.forecast(df, h=12, freq="MS")
+    ```
+
+    **License note:** TimesFM 3.0 pretrained weights are [non-commercial](https://huggingface.co/google/timesfm-3.0-pytorch/blob/main/LICENSE); TimesFM 1.0–2.5 checkpoints remain Apache-2.0.
+
+* **GIFT-Eval**: Registered `google--timesfm-3.0-pytorch` (reference slug `TimesFM-3`) in the gift-eval model registry and added it to the CI replication subset on `m4_weekly/short`.
+
+* **TimesFM family notebook**: Added [`timesfm-family` example notebook](../examples/timesfm-family.ipynb) comparing TimesFM 1.0, 2.0, 2.5, and 3.0 with supported prediction intervals.
+
+### Dependencies
+
+* Bumped `timecopilot-timesfm` from `>=0.3.0` to `>=0.4.0`.
+
+### Documentation
+
+* Updated README, model hub, and `TimesFM` docstrings with TimesFM 3.0 support and non-commercial license citation.
+
+---
+
+**Full Changelog**: https://github.com/TimeCopilot/foundationforecast/compare/v0.1.2...v0.1.3

docs/examples/index.md

@@ -17,6 +17,7 @@ For model API details, see the [Model Hub](../model-hub.md).
 | Notebook | What you'll learn | Prerequisites |
 |----------|-------------------|---------------|
 | [Chronos Family](chronos-family.ipynb) | Forecast with Chronos 1.x and 2.x checkpoints | Python 3.10+ |
+| [TimesFM Family](timesfm-family.ipynb) | Forecast with TimesFM 1.0, 2.0, 2.5, and 3.0 with prediction intervals | Python 3.10+ |
 | [TiRex Family](tirex-family.ipynb) | Forecast with TiRex 1.0 and 2.0 | Python 3.11+ |
 | [Toto Family](toto-family.ipynb) | Forecast with Toto 1.0 and 2.0 | Python 3.10+ |
 | [Finetuning](finetuning.ipynb) | Adapt Chronos 2 and TimeGPT to your data | Python 3.10+; GPU recommended |

mkdocs.yml

@@ -26,6 +26,7 @@ nav:
       - Compare Foundation Models: examples/ts-foundation-models-comparison-quickstart.ipynb
       - Family Guides:
           - Chronos: examples/chronos-family.ipynb
+          - TimesFM: examples/timesfm-family.ipynb
           - TiRex: examples/tirex-family.ipynb
           - Toto: examples/toto-family.ipynb
       - Finetuning: examples/finetuning.ipynb
@@ -36,6 +37,10 @@ nav:
   - Community:
       - Getting Help: community/help.md
       - Contributing: contributing.md
+  - Changelogs:
+      - changelogs/index.md
+      - changelogs/v0.1.3.md
+      - changelogs/v0.1.2.md
 
 theme:
   name: material

pyproject.toml

@@ -28,6 +28,22 @@ docs = [
 authors = [
   {email = "azul.garza.r@gmail.com", name = "Azul Garza"},
 ]
+classifiers = [
+  "Development Status :: 2 - Pre-Alpha",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Information Technology",
+  "License :: OSI Approved :: Apache Software License",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+  "Topic :: Software Development :: Libraries :: Python Modules",
+]
 dependencies = [
   "gluonts[torch]",
   "huggingface-hub>=0.36.2,<2.0",
@@ -55,7 +71,7 @@ license = "Apache-2.0"
 name = "foundationforecast"
 readme = "README.md"
 requires-python = ">=3.10"
-version = "0.1.2"
+version = "0.1.3"
 
 [project.optional-dependencies]
 plot = [

tests/docs/test_docs.py

@@ -1,3 +1,4 @@
+import re
 from pathlib import Path
 
 import pytest
@@ -7,7 +8,7 @@
 @pytest.mark.docs
 @pytest.mark.parametrize(
     "fpath",
-    [p for p in Path("docs").rglob("*.md")],
+    [p for p in Path("docs").rglob("*.md") if "changelogs" not in p.parts],
     ids=str,
 )
 @pytest.mark.flaky(reruns=3, reruns_delay=80)
@@ -21,6 +22,21 @@ def test_readme():
     check_md_file("README.md", memory=True)
 
 
+@pytest.mark.docs
+def test_latest_changelog():
+    def version_key(filename):
+        match = re.search(r"(\d+\.\d+\.\d+)", str(filename))
+        if match:
+            version_string = match.group(1)
+            return tuple(map(int, version_string.split(".")))
+        return (0, 0, 0)
+
+    changelog_dir = Path("docs/changelogs")
+    changelogs = sorted(changelog_dir.glob("v*.md"), key=version_key)
+    latest_changelog = changelogs[-1] if changelogs else None
+    check_md_file(latest_changelog, memory=True)
+
+
 @pytest.mark.docs
 @pytest.mark.parametrize(
     "fpath",