Kairos-10M
Model directorymldi-lab/Kairos_10m9.95M params | Upstream checkpoint
Kairos-10M is the smallest public checkpoint in the Kairos family, developed by researchers from Ant Group and ShanghaiTech University. It is positioned as an adaptive zero-shot forecaster, and at roughly 10M parameters it is the lightest-weight way to access the Kairos design while staying entirely in the zero-shot regime.
Architecturally it is an encoder-decoder transformer whose defining feature is adaptivity: the official model cards and project page describe adaptive tokenization paired with instance-adaptive rotary position encoding, so the model varies its patching granularity and positional treatment to match the local information density and temporal structure of each series. It is pretrained on the PreSTS corpus of 300B+ time points, which gives the small checkpoint its broad zero-shot reach across heterogeneous domains.
Where to run this model
Compute availability, hardware requirements, and pricing depend on the execution provider.
Get model weights, deployment instructions, and current provider listings.
Hugging Face provider mappings checked 2026-10-06. No Inference Provider mapping was listed for this checkpoint.
Model Classification
Family
Kairos
Type
time series foundation model
Pretrained time-series model for zero-shot or few-shot forecasting workloads.
Resources
Training Data
PreSTS corpus with 300B+ time points, as documented by the official Kairos model cards and project page.
Recommended For
- • Adaptive zero-shot forecasting across heterogeneous series
- • Teams that want a mid-size open family with modern tokenization ideas
Strengths
- • Adaptive tokenization handles changing information density well
- • Clear parameter-size ladder from small to larger public checkpoints
Limitations
- • Newer family with a smaller production footprint than the most established lines
- • Focused on forecasting rather than general multi-task time-series tooling
Capabilities
Tags
Specifications
- Parameters
- 9.95M
- Architecture
- encoder-decoder transformer with adaptive patching and instance-adaptive rotary position encoding
- Context length
- n/a
- Max context
- n/a
- Minimum history
- n/a
- Recommended history
- n/a
- Input step
- n/a
- Required target series
- 1
- Temperature
- Ignored
- Top P
- Ignored
- Max output
- n/a
- License
- n/a