add new version detail
Browse files
README.md
CHANGED
|
@@ -1,15 +1,16 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
-
|
| 5 |
-
|
| 6 |
pipeline_tag: time-series-forecasting
|
| 7 |
paper:
|
| 8 |
-
|
| 9 |
tags:
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
|
|
|
| 13 |
---
|
| 14 |
# Cisco Time Series Model
|
| 15 |
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](https://huggingface.co/google/timesfm-2.0-500m-pytorch), with multiresolution modifications aimed at efficient use of long context. It expects a multiresolution context (x<sub>c</sub>, x<sub>f</sub>), where the resolution (i.e., space between data points) of x<sub>c</sub> is 60 times the resolution of x<sub>f</sub>. Both x<sub>c</sub> and x<sub>f</sub> can have length up to 512. The input contexts should be aligned “on the right,” e.g., if x<sub>f</sub> consists of the 512 minutes terminating at 11:00AM on November 11, then x<sub>c</sub> 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.
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
+
- Salesforce/GiftEvalPretrain
|
| 5 |
+
- autogluon/chronos_datasets
|
| 6 |
pipeline_tag: time-series-forecasting
|
| 7 |
paper:
|
| 8 |
+
- https://arxiv.org/abs/2511.19841
|
| 9 |
tags:
|
| 10 |
+
- time series
|
| 11 |
+
- foundation model
|
| 12 |
+
- forecasting
|
| 13 |
+
new_version: cisco-ai/cisco-time-series-model-1.0
|
| 14 |
---
|
| 15 |
# Cisco Time Series Model
|
| 16 |
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](https://huggingface.co/google/timesfm-2.0-500m-pytorch), with multiresolution modifications aimed at efficient use of long context. It expects a multiresolution context (x<sub>c</sub>, x<sub>f</sub>), where the resolution (i.e., space between data points) of x<sub>c</sub> is 60 times the resolution of x<sub>f</sub>. Both x<sub>c</sub> and x<sub>f</sub> can have length up to 512. The input contexts should be aligned “on the right,” e.g., if x<sub>f</sub> consists of the 512 minutes terminating at 11:00AM on November 11, then x<sub>c</sub> 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.
|