Task
Time Series Forecasting
C
cisco-ai/cisco-time-series-model-1.0-preview
Time Series Forecasting·cisco-ai· 729· 19
apache-2.0
Time Series Forecasting
498.8M params
dataset:Salesforce/GiftEvalPretraindataset:autogluon/chronos_datasetsarxiv:2511.19841license:apache-2.0region:us
Cisco Time Series Model The Cisco Time Series Model is a foundation model trained to perform univariate zero-shot forecasting. Its core is a sequence of decoder-only transformer layers. It is based on the TimesFM2.0 model, with multiresolution modifications aimed at efficient use of long context. It expects a multiresolution context (xc, xf), where the resolution (i.e., space between data points)
# pull & run locally
pip install mlforge-sdk && mlforge pull cisco-ai/cisco-time-series-model-1.0-preview
pip install mlforge-sdk && mlforge pull cisco-ai/cisco-time-series-model-1.0-preview
Model details
Provider
cisco-ai
Parameters
498.8M
Size
3.7 GB
License
apache-2.0
Downloads
729
Likes
19
Paper
arXiv:2511.19841
Updated
2026-03-09
About cisco-ai/cisco-time-series-model-1.0-preview
Cisco Time Series Model The Cisco Time Series Model is a foundation model trained to perform univariate zero-shot forecasting. Its core is a sequence of decoder-only transformer layers. It is based on the TimesFM2.0 model, with multiresolution modifications aimed at efficient use of long context. It expects a multiresolution context (xc, xf), where the resolution (i.e., space between data points) of xc is 60 times the resolution of xf. Both xc and xf can have length up to 512. The input contexts should be aligned “on the right,” e.g., if xf consists of the 512 minutes terminating at 11:00AM on November 11, then xc should consist of the 512 hours terminating at the same time. The output is a forecast of 128 points, which should be interpreted at the finer resolution; and corresponding quantiles for these points.