ci-proto / README.md

Add model card

ee30313 verified 2 days ago

5.51 kB

---
license: other
license_name: ci-proto-licence
license_link: https://huggingface.co/ContinuousIntelligence/ci-proto/blob/main/LICENCE
library_name: continuousintelligence
pipeline_tag: time-series-forecasting
tags:
- time-series
- forecasting
- probabilistic-forecasting
- foundation-model
---
<img src="assets/readme/header.svg" alt="ci-proto · Continuous Intelligence" width="1200">

# Introducing ci-proto, our frontier model that says goodbye to context windows and hello to accuracy

**State-of-the-art forecasting at your fingertips.**

- **2M+ context window.** Process 64× the history of any other time-series foundation
  model.
- **Frontier accuracy.** Leading forecasting performance on fev-bench.
- **CPU and GPU support.** Run locally through the same Python API.
- **Multivariate forecasting.** Turn relationships between signals into more accurate
  forecasts.
- **Uncertainty included.** Get nine quantiles between 0.1 and 0.9 to plan for a range of
  outcomes.

**[Make your first forecast](#make-your-first-forecast) ·
[See the results](#frontier-performance) ·
[Join the waitlist for our next release](https://www.continuousintelligence.co.uk/waitlist) ·
[Join our Design Partner Program](https://docs.google.com/forms/d/e/1FAIpQLSdn59prmnz5KpJtVQlyo1FFGLA_YgIB93Z5E5pVIvpTYBnFuw/viewform)**

## Make your first forecast

**Your first forecast in a few lines.** Install with Python 3.10–3.14:

```sh
pip install continuousintelligence
```

Forecast the next day of bicycle rentals from five observed days of hourly demand
in Washington, D.C. The example history is included with the package:

```python
import continuousintelligence as ci
# Load the model (uses CUDA when available).
model = ci.load_model("ContinuousIntelligence/ci-proto")
# Load example history as a torch.Tensor shaped [variables, time].
history = ci.load_example()
# Forecast the next 24 hourly time steps.
prediction = model.forecast(history, horizon=24)
# Plot the forecast and its uncertainty bands.
ci.plot_forecast(history, prediction, model.quantiles, output="forecast.png")
```

![Five days of hourly bicycle rentals followed by ci-proto's next-day median
forecast and nested quantile bands.](assets/readme/bike_sharing_forecast.png)

**The next 24 hours, with uncertainty included.** The shaded region marks the forecast
day. The curve shows the model's median forecast, surrounded by nested quantile bands.
Replace the example history with your own to get started.

Data: Hadi Fanaee-T (2013), [Bike Sharing, UCI](https://doi.org/10.24432/C5W894),
licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).

**Dive deeper.** The [walkthrough notebook][walkthrough] extends this example with calendar
covariates, practical uses of the quantiles, and forecasting through missing data.

[walkthrough]: https://github.com/continuousintelligence/ci/blob/main/examples/walkthrough.ipynb

## Frontier performance

**The #1 foundation model on fev-bench.**

![Mean scaled quantile loss on fev-bench versus parameter count for ci-proto and other
forecasting models. Lower is better.](assets/readme/ci_proto_pareto_frontier.png)
## Talk to the team
**Tell us what you need to predict.** We want to hear about the decisions you're trying to
improve, the data you're working with, and where current methods fall short.
Whether you're exploring a new idea or improving an existing system, we'd like to work
with you on a solution. Share your use case, your constraints, and what success would look
like, and let's discuss how we can help.
**[Join our Design Partner Program](https://docs.google.com/forms/d/e/1FAIpQLSdn59prmnz5KpJtVQlyo1FFGLA_YgIB93Z5E5pVIvpTYBnFuw/viewform)**
## Beyond ci-proto
**Frontier performance is our starting point.** ci-proto gives you a first look at our
approach to time-series intelligence. Our next release builds on that foundation.
Join the waitlist to be the first to hear what's new, see the results, and find out when
you can try it.
**[Join the waitlist](https://www.continuousintelligence.co.uk/waitlist)**
## Usage details
Covariates, categorical inputs, timestamps, related series, revision pinning, and CPU and
GPU setup are documented in the [package README](https://github.com/continuousintelligence/ci#usage-details).
## Model details
- **Developed by:** Continuous Intelligence Limited
- **Model type:** pretrained time-series foundation model for zero-shot probabilistic forecasting
- **Parameters:** 167M
- **Inputs:** one or more target series, with optional past and future covariates, timestamps and related series
- **Outputs:** nine quantiles from 0.1 to 0.9 for every target and forecast step
- **Files:** `model.ckpt` (histories up to 16,384 steps), `model-long.ckpt` (longer histories, selected
  automatically), `tta.json` (preprocessing and calibration settings) and `config.json` (model information)
## Training and evaluation
- **Training data:** a large corpus of real-world and synthetic time series.
- **Evaluation:** zero-shot on all 100 tasks of [fev-bench](https://huggingface.co/spaces/autogluon/fev-leaderboard),
  with the released preprocessing and calibration in `tta.json`, scored by scaled quantile loss.
## Licence
The model weights are released under the [ci-proto Code and Model Licence](LICENCE).
## Citation
```bibtex
@misc{ci-proto-2026,
  title  = {ci-proto},
  author = {{Continuous Intelligence Limited}},
  year   = {2026},
  url    = {https://huggingface.co/ContinuousIntelligence/ci-proto}
}
```

	---
	license: other
	license_name: ci-proto-licence
	license_link: https://huggingface.co/ContinuousIntelligence/ci-proto/blob/main/LICENCE
	library_name: continuousintelligence
	pipeline_tag: time-series-forecasting
	tags:
	- time-series
	- forecasting
	- probabilistic-forecasting
	- foundation-model
	---

	<img src="assets/readme/header.svg" alt="ci-proto · Continuous Intelligence" width="1200">

	# Introducing ci-proto, our frontier model that says goodbye to context windows and hello to accuracy

	State-of-the-art forecasting at your fingertips.

	- 2M+ context window. Process 64× the history of any other time-series foundation
	model.
	- Frontier accuracy. Leading forecasting performance on fev-bench.
	- CPU and GPU support. Run locally through the same Python API.
	- Multivariate forecasting. Turn relationships between signals into more accurate
	forecasts.
	- Uncertainty included. Get nine quantiles between 0.1 and 0.9 to plan for a range of
	outcomes.

	**[Make your first forecast](#make-your-first-forecast) ·
	[See the results](#frontier-performance) ·
	[Join the waitlist for our next release](https://www.continuousintelligence.co.uk/waitlist) ·
	[Join our Design Partner Program](https://docs.google.com/forms/d/e/1FAIpQLSdn59prmnz5KpJtVQlyo1FFGLA_YgIB93Z5E5pVIvpTYBnFuw/viewform)**

	## Make your first forecast

	Your first forecast in a few lines. Install with Python 3.10–3.14:

	```sh
	pip install continuousintelligence
	```

	Forecast the next day of bicycle rentals from five observed days of hourly demand
	in Washington, D.C. The example history is included with the package:

	```python
	import continuousintelligence as ci

	# Load the model (uses CUDA when available).
	model = ci.load_model("ContinuousIntelligence/ci-proto")

	# Load example history as a torch.Tensor shaped [variables, time].
	history = ci.load_example()

	# Forecast the next 24 hourly time steps.
	prediction = model.forecast(history, horizon=24)

	# Plot the forecast and its uncertainty bands.
	ci.plot_forecast(history, prediction, model.quantiles, output="forecast.png")
	```

	![Five days of hourly bicycle rentals followed by ci-proto's next-day median
	forecast and nested quantile bands.](assets/readme/bike_sharing_forecast.png)

	The next 24 hours, with uncertainty included. The shaded region marks the forecast
	day. The curve shows the model's median forecast, surrounded by nested quantile bands.
	Replace the example history with your own to get started.

	Data: Hadi Fanaee-T (2013), [Bike Sharing, UCI](https://doi.org/10.24432/C5W894),
	licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).

	Dive deeper. The [walkthrough notebook][walkthrough] extends this example with calendar
	covariates, practical uses of the quantiles, and forecasting through missing data.

	[walkthrough]: https://github.com/continuousintelligence/ci/blob/main/examples/walkthrough.ipynb

	## Frontier performance

	The #1 foundation model on fev-bench.

	![Mean scaled quantile loss on fev-bench versus parameter count for ci-proto and other
	forecasting models. Lower is better.](assets/readme/ci_proto_pareto_frontier.png)

	## Talk to the team

	Tell us what you need to predict. We want to hear about the decisions you're trying to
	improve, the data you're working with, and where current methods fall short.

	Whether you're exploring a new idea or improving an existing system, we'd like to work
	with you on a solution. Share your use case, your constraints, and what success would look
	like, and let's discuss how we can help.

	[Join our Design Partner Program](https://docs.google.com/forms/d/e/1FAIpQLSdn59prmnz5KpJtVQlyo1FFGLA_YgIB93Z5E5pVIvpTYBnFuw/viewform)

	## Beyond ci-proto

	Frontier performance is our starting point. ci-proto gives you a first look at our
	approach to time-series intelligence. Our next release builds on that foundation.
	Join the waitlist to be the first to hear what's new, see the results, and find out when
	you can try it.

	[Join the waitlist](https://www.continuousintelligence.co.uk/waitlist)

	## Usage details

	Covariates, categorical inputs, timestamps, related series, revision pinning, and CPU and
	GPU setup are documented in the [package README](https://github.com/continuousintelligence/ci#usage-details).

	## Model details

	- Developed by: Continuous Intelligence Limited
	- Model type: pretrained time-series foundation model for zero-shot probabilistic forecasting
	- Parameters: 167M
	- Inputs: one or more target series, with optional past and future covariates, timestamps and related series
	- Outputs: nine quantiles from 0.1 to 0.9 for every target and forecast step
	- Files: `model.ckpt` (histories up to 16,384 steps), `model-long.ckpt` (longer histories, selected
	automatically), `tta.json` (preprocessing and calibration settings) and `config.json` (model information)

	## Training and evaluation

	- Training data: a large corpus of real-world and synthetic time series.
	- Evaluation: zero-shot on all 100 tasks of [fev-bench](https://huggingface.co/spaces/autogluon/fev-leaderboard),
	with the released preprocessing and calibration in `tta.json`, scored by scaled quantile loss.

	## Licence

	The model weights are released under the [ci-proto Code and Model Licence](LICENCE).

	## Citation

	```bibtex
	@misc{ci-proto-2026,
	title = {ci-proto},
	author = {{Continuous Intelligence Limited}},
	year = {2026},
	url = {https://huggingface.co/ContinuousIntelligence/ci-proto}
	}
	```