CHARM

CHARM (CHannel-Aware Representation Model) is C3 AI's foundation model for multivariate time series. It is served behind an API and consumed through the open-source c3-charm Python SDK:

• Embeddings: turn (T, C) windows into dense vectors for search, clustering, anomaly detection and features.
• Zero-shot forecasting: quantile forecasts and backcasts with no training data.
• Toolkit (charm_toolkit): anomaly-detection recipes, retrieval metrics, and small trainable heads for forecasting, reconstruction and classification.

The model is channel-aware (channel names are part of the input) and normalizes internally, so you send raw values. It runs server-side; the SDK is the client.

Availability: CHARM model weights and training/replication code are not publicly released. The model is served behind an API and consumed through the c3-charm SDK.

Use it

📖 Docs & quickstart: c3aiia3c-charm-docs.static.hf.space — introduction, quick start, example use cases, and using CHARM with coding agents.

pip install c3-charm   # Python >= 3.10

Full SDK documentation (install, data format, client, embeddings, forecasting, anomaly detection, trained heads, HTTP API) ships inside the package — find it with python -c "import charm.docs as d; print(d.get_docs_path())" and start at index.md. Package: c3-charm on PyPI.

Getting access

CHARM is served behind an API. Set CHARM_BASE_URL and CHARM_API_KEY to point the SDK at an endpoint. To obtain access, contact gerardo.pastrana@c3.ai and dhruv.mehta@c3.ai.

The model will also be available on Azure AI Foundry — deployment instructions will be added here.

Using an AI coding agent?

The CHARM agent skill teaches Claude Code, Cursor, Codex and others when and how to apply CHARM. Install it:

claude plugin marketplace add https://huggingface.co/c3aiia3c/CHARM.git
claude plugin install charm@c3-charm

Other agents, manual install, and example prompts: see the docs site or skills/charm/README.md.

Example notebooks

Runnable notebooks (with sample data) live in notebooks/. The notebooks use the toolkit, which needs PyTorch — install the CPU wheel first, then the toolkit:

pip install torch --index-url https://download.pytorch.org/whl/cpu
pip install "c3-charm[toolkit]"

Then set CHARM_BASE_URL / CHARM_API_KEY and run them locally.

Notebook	What it covers
getting_started.ipynb	Client setup, first embeddings call, inspecting model_info()
charm_toolkit_demo.ipynb	Tour of the toolkit: datasets, precompute, trainer, each task head
demo_forecasting.ipynb	Zero-shot forecasting and the embedding-based ForecastingModel head
demo_reconstruction.ipynb	Backcast reconstruction and the ReconstructionModel head
demo_classification.ipynb	Time-series classification with the ClassificationModel head
demo_retrieval_anomaly_detection.ipynb	Embedding retrieval + kNN / zero-shot anomaly-detection recipes

Model summary

Parameters	~63.3M (encoder ~59M)
Hidden size (d_model)	384
Projection	TCN-pool (patch size 16, causal conv stack + residual gate)
Backbone	Transformer encoder with RoPE attention
Decoder	Quantile decoder, 99 levels (0.01–0.99)
Max context length	8192
Output	Probabilistic (quantile) forecasts, multivariate-capable
Precision	float32

Intended use

Zero-shot probabilistic forecasting of univariate and multivariate time series across domains (energy, transport, sales, healthcare, nature, web/cloud-ops, econ/finance). The model is applied without any per-dataset fine-tuning.

GIFT-Eval results

Evaluated zero-shot on the full GIFT-Eval benchmark (97 dataset/frequency/term configurations) using the standard 11-metric protocol. Aggregate scores (geometric mean of per-config metrics normalized to the Seasonal Naive baseline; lower is better):

Metric	Score (rel. Seasonal Naive)
MASE	0.7582
CRPS (mean weighted sum quantile loss)	0.4776

Per-term (geometric mean, normalized to Seasonal Naive):

Term	MASE	CRPS
short	0.7463	0.5036
medium	0.7577	0.4452
long	0.7911	0.4460

Scores are the geometric mean of per-config metric / Seasonal Naive across all 97 GIFT-Eval configurations (lower is better; < 1.0 beats Seasonal Naive).

Evaluation protocol

• Benchmark: GIFT-Eval, 97 configs (short / medium / long terms).
• Metrics: MSE[mean], MSE[0.5], MAE[0.5], MASE[0.5], MAPE[0.5], sMAPE[0.5], MSIS, RMSE[mean], NRMSE[mean], ND[0.5], mean_weighted_sum_quantile_loss (computed with gluonts evaluate_forecasts).
• Context length: 8192; forecasts are full quantile distributions.
• Zero-shot: no GIFT-Eval train/test data is seen during pretraining (testdata_leakage = No).

Limitations

• Forecast quality varies by domain and horizon; very long horizons and highly non-stationary series remain challenging.
• Quantile calibration is learned and may drift on out-of-distribution scales.

Paper

Utsav Dutta, Gerardo Pastrana, Sina Khoshfetrat Pakazad, Henrik Ohlsson. Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings. ICML 2026. arXiv:2605.31580 · Hugging Face Papers

Citation

@inproceedings{dutta2026charm,
  title     = {Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings},
  author    = {Dutta, Utsav and Pastrana, Gerardo and Khoshfetrat Pakazad, Sina and Ohlsson, Henrik},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning (ICML)},
  series    = {Proceedings of Machine Learning Research},
  volume    = {306},
  year      = {2026},
  url       = {https://arxiv.org/abs/2605.31580},
}

License

Apache License 2.0 for the SDK and skill. See c3-charm on PyPI. Model weights are not released.