Skip to content
Other

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 moreDetails
Benchmarks: 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.
Discuss Telegram 0 180

Will it run?

Runs in F32

Fits without quantisation.

  • F32weights 0.4 GB · ready files0.9 GB
  • BF16weights 0.2 GB0.7 GB
  • FP8 / INT8recommendedweights 0.1 GB0.6 GB
  • 4-bitweights 0.0 GB0.6 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · F32 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # thu-sail-lab/Anlu
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download thu-sail-lab/Anlu --local-dir ~/models/Anlu
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to Anlu
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of Anlu (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

thu-sail-lab/Anlu
Author
thu-sail-lab
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

1800

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments

Other

Le Dog

Le Dog