File size: 7,683 Bytes

---
license: openmdw-1.1
library_name: simons
pipeline_tag: time-series-forecasting
datasets:
- abel-lab/Simons-Pretrain
thumbnail: https://huggingface.co/abel-lab/Simons-297M/resolve/main/assets/abel-color.png
tags:
- time-series
- forecasting
- probabilistic-forecasting
- foundation-model
- covariates
- pretrained
- pytorch
model-index:
- name: Simons-297M
  results:
  - task:
      type: time-series-forecasting
    dataset:
      name: GIFT-Eval
      type: Salesforce/GiftEval
    metrics:
    - name: MASE (relative to Seasonal Naive)
      type: mase
      value: 0.6731
    - name: CRPS (relative to Seasonal Naive)
      type: crps
      value: 0.4574
    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: 48.41
    - name: MASE skill score (%, relative to Seasonal Naive)
      type: mase
      value: 37.85
    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: 0.6371
    - name: CRPS (relative to Seasonal Naive)
      type: crps
      value: 0.5341
    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-297M/resolve/main/assets/abel-color.png" alt="Abel"
width="240" />
  <img class="hidden dark:block"
src="https://huggingface.co/abel-lab/Simons-297M/resolve/main/assets/abel-white.png" alt="Abel"
width="240" />
</p>

# Simons-297M

[![GitHub: Abel-ai-lab/Simons](https://img.shields.io/badge/GitHub-Abel--ai--lab%2FSimons-24292F?logo=github)](https://github.com/Abel-ai-lab/Simons)
[![Data: Simons-Pretrain](https://img.shields.io/badge/Data-Simons--Pretrain-FFD21E?logo=huggingface&logoColor=black)](https://huggingface.co/datasets/abel-lab/Simons-Pretrain)

Simons-297M 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:** 297.2M parameters.
- **Architecture:** a causal transformer over patches of 32 time steps, then an attention layer
  across the variates of a series; 13 layers, width 1280, 20 heads.
- **Context and horizon:** up to 32,768 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 equal-weight average of the stage-3 model and its continuation (WiSE-FT).
- **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-297M/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-297M/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-297M/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-297M/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-297M", 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}
}
```