| --- |
| license: openmdw-1.1 |
| library_name: simons |
| pipeline_tag: time-series-forecasting |
| datasets: |
| - abel-lab/Simons-Pretrain |
| thumbnail: https://huggingface.co/abel-lab/Simons-25M/resolve/main/assets/abel-color.png |
| tags: |
| - time-series |
| - forecasting |
| - probabilistic-forecasting |
| - foundation-model |
| - covariates |
| - pretrained |
| - pytorch |
| model-index: |
| - name: Simons-25M |
| results: |
| - task: |
| type: time-series-forecasting |
| dataset: |
| name: GIFT-Eval |
| type: Salesforce/GiftEval |
| metrics: |
| - name: MASE (relative to Seasonal Naive) |
| type: mase |
| value: 0.6860 |
| - name: CRPS (relative to Seasonal Naive) |
| type: crps |
| value: 0.4683 |
| source: |
| name: GIFT-Eval leaderboard |
| url: https://huggingface.co/spaces/Salesforce/GIFT-Eval |
| - task: |
| type: time-series-forecasting |
| dataset: |
| name: fev-bench |
| type: autogluon/fev_datasets |
| metrics: |
| - name: SQL skill score (%, relative to Seasonal Naive) |
| type: sql |
| value: 47.74 |
| - name: MASE skill score (%, relative to Seasonal Naive) |
| type: mase |
| value: 36.27 |
| source: |
| name: fev-bench leaderboard |
| url: https://huggingface.co/spaces/autogluon/fev-bench |
| - task: |
| type: time-series-forecasting |
| dataset: |
| name: TIME |
| type: Real-TSF/TIME |
| metrics: |
| - name: MASE (relative to Seasonal Naive) |
| type: mase |
| value: 0.6473 |
| - name: CRPS (relative to Seasonal Naive) |
| type: crps |
| value: 0.5426 |
| source: |
| name: TIME leaderboard |
| url: https://huggingface.co/spaces/Real-TSF/TIME-leaderboard |
| --- |
| |
| <p align="center"> |
| <img class="dark:hidden" |
| src="https://huggingface.co/abel-lab/Simons-25M/resolve/main/assets/abel-color.png" alt="Abel" |
| width="240" /> |
| <img class="hidden dark:block" |
| src="https://huggingface.co/abel-lab/Simons-25M/resolve/main/assets/abel-white.png" alt="Abel" |
| width="240" /> |
| </p> |
|
|
| # Simons-25M |
|
|
| [](https://github.com/Abel-ai-lab/Simons) |
| [](https://huggingface.co/datasets/abel-lab/Simons-Pretrain) |
|
|
| Simons-25M is an open time series foundation model from Abel AI Lab for probabilistic forecasting. |
| It supports univariate and multivariate series with known-future covariates. |
| The [GitHub repository](https://github.com/Abel-ai-lab/Simons) contains inference and training code. |
| The release post, [Introducing Simons](https://abel.ai/research/introducing-simons/), tells how the models were built. |
| All four sizes and the training data are in the [Simons 1](https://huggingface.co/collections/abel-lab/simons-1-6ae3d4ce9705938e293c52dd) collection. |
| The [Simons Forecast Explorer](https://huggingface.co/spaces/abel-lab/simons-forecast-explorer) shows forecasts of the four sizes in the browser. |
|
|
| ## Model details |
|
|
| - **Size:** 25.1M parameters. |
| - **Architecture:** a causal transformer over patches of 32 time steps, then an attention layer |
| across the variates of a series; 12 layers, width 384, 6 heads. |
| - **Context and horizon:** up to 16,384 time steps of history; 512 steps per forward pass, longer |
| horizons block by block. |
| - **Inputs:** up to 32 variates and up to 16 known-future covariates per series, numeric or |
| categorical; NaN marks missing values. Past-only covariates are accepted and dropped. |
| - **Outputs:** 9 quantiles (0.1, 0.2, ..., 0.9). |
| - **Training:** four stages, from synthetic pretraining to post-training on real data; the released |
| weights are the uniform average of the two continuations (Model soups). |
| - **Inference:** PyTorch on CPU or GPU, with the `simons` package, version 0.1.0 or later. |
|
|
| ## Benchmarks |
|
|
| <p align="center"> |
| <img class="dark:hidden" |
| src="https://huggingface.co/abel-lab/Simons-25M/resolve/main/assets/benchmark-places.png" alt="Places on public benchmark leaderboards" |
| width="720" /> |
| <img class="hidden dark:block" |
| src="https://huggingface.co/abel-lab/Simons-25M/resolve/main/assets/benchmark-places-dark.png" alt="Places on public benchmark leaderboards" |
| width="720" /> |
| </p> |
|
|
| The place of Simons-297M and four widely used models on each benchmark. On |
| [GIFT-Eval](https://huggingface.co/spaces/Salesforce/GIFT-Eval), [fev-bench](https://huggingface.co/spaces/autogluon/fev-bench) and [TIME](https://huggingface.co/spaces/Real-TSF/TIME-leaderboard) the places are among the open-weight entries. |
|
|
| ### Efficiency |
|
|
| Simons is fast to run: on one A100 GPU, Simons-297M forecasts a whole benchmark in minutes, about ten |
| times faster than models of similar size. |
|
|
| <p align="center"> |
| <img class="dark:hidden" |
| src="https://huggingface.co/abel-lab/Simons-25M/resolve/main/assets/inference-time.png" alt="Time to forecast GIFT-Eval, TIME and fev-bench" |
| width="720" /> |
| <img class="hidden dark:block" |
| src="https://huggingface.co/abel-lab/Simons-25M/resolve/main/assets/inference-time-dark.png" alt="Time to forecast GIFT-Eval, TIME and fev-bench" |
| width="720" /> |
| </p> |
|
|
| ## Get started |
|
|
| ```shell |
| pip install "git+https://github.com/Abel-ai-lab/Simons" |
| ``` |
|
|
| ```python |
| import torch |
| from simons import Simons |
| |
| device = "cuda" if torch.cuda.is_available() else "cpu" |
| model = Simons.from_pretrained("abel-lab/Simons-25M", device=device) |
| |
| # [batch, time] or [batch, variates, time]; NaN marks missing values |
| history = torch.randn(8, 2000).cumsum(-1) |
| quantiles = model.forecast(history, horizon=96) # [8, 96, 9] |
| |
| # Known-future covariates: [batch, covariates, time + horizon] |
| covariates = torch.randn(8, 2, 2000 + 96) |
| quantiles = model.forecast(history, horizon=96, covariates=covariates) |
| ``` |
|
|
| - **Training data:** [abel-lab/Simons-Pretrain](https://huggingface.co/datasets/abel-lab/Simons-Pretrain), |
| the public part of the data the models were trained on. |
| - **Getting started:** [docs/GETTING_STARTED.md](https://github.com/Abel-ai-lab/Simons/blob/main/docs/GETTING_STARTED.md) covers the input format, |
| covariates, forecast options and fine-tuning. |
| - **Models:** [docs/MODEL.md](https://github.com/Abel-ai-lab/Simons/blob/main/docs/MODEL.md) compares the four sizes and gives their scores. |
| - **Training:** [docs/TRAINING.md](https://github.com/Abel-ai-lab/Simons/blob/main/docs/TRAINING.md) covers the stages, configs and GPU settings. |
| - **Data:** [docs/DATA.md](https://github.com/Abel-ai-lab/Simons/blob/main/docs/DATA.md) describes what the models were trained on. |
|
|
| ## Training data |
|
|
| - Synthetic series from the open generators in |
| [`src/simons/synth`](https://github.com/Abel-ai-lab/Simons/tree/main/src/simons/synth), with |
| synthetic known-future covariates of known effect. |
| - Public datasets with a permissive or share-alike license, most of them released as |
| [abel-lab/Simons-Pretrain](https://huggingface.co/datasets/abel-lab/Simons-Pretrain). |
| - Internal data: an in-house corpus. |
|
|
| See the |
| [dataset](https://huggingface.co/datasets/abel-lab/Simons-Pretrain) for data details |
| and the [training quickstart](https://github.com/Abel-ai-lab/Simons#train) for training commands. |
| Notices required by the training data's licenses: [NOTICE.md](NOTICE.md). |
|
|
| ## License |
|
|
| The weights are licensed under OpenMDW-1.1 ([LICENSE](LICENSE)); the code on GitHub is licensed |
| under Apache-2.0 ([LICENSE](https://github.com/Abel-ai-lab/Simons/blob/main/LICENSE)). Each training |
| dataset keeps its own license; see [NOTICE.md](NOTICE.md) for details. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @misc{simons2026, |
| title = {Simons: Building Open Time Series Foundation Models through Auto-Research}, |
| author = {{Abel AI Lab}}, |
| year = {2026}, |
| url = {https://github.com/Abel-ai-lab/Simons} |
| } |
| ``` |
|
|
