Anlu s38000
Time-series anomaly detector
1 min readupdated
Anlu is a pretrained time-series anomaly detector that uses a normal reference prefix to interpret queries and returns an anomaly score for every timestamp. The model contains about 90 million parameters in Safetensors format and includes both encoders, a resampler, adapters, and output heads. The tool is designed for researchers and engineers working with time series in the TSB-AD ecosystem.
Key features
- Around 90 million parameters in a single Safetensors checkpoint
- Frozen weights during inference for stable performance
- Full compatibility with the TSB-AD library
- Validation on univariate input data
What you can do
- Integrate the model into a TSB-AD pipeline for time-series analysis
- Run anomaly scoring using the Python script from the model card
- Use it as a ready-to-go detector without fine-tuning on specific datasets
Example
from TSB_AD.models.Anlu import Anlu
# Arrays have shape [time, 1]. No labels are supplied to the model.
detector = Anlu(device="cuda:0")
detector.fit(normal_prefix)
scores = detector.decision_function(query)Read more
DetailsBenchmarks: Full-series VUS-PR is 0.599280663 on 350 TSB-AD-U records.
Requirements: PyTorch and the TSB-AD library are required.
Limitations: Validated for univariate inputs; it is not a causal streaming detector.








Comments