NEWVectors or files. Pick a path.Start →
    Served on MixpeekClassificationVerified 2026-11-05

    DistilBERT NSFW text classifier

    eliasalbouzidi/distilbert-nsfw-text-classifier

    DistilBERT NSFW text classifier is a text classification model (Apache-2.0). Served on Mixpeek, scaling to zero when idle.

    A Ray Serve app in Mixpeek's inference registry hosts it. It starts at zero replicas and wakes on first use.

    Use in a new namespaceAdd to an existing namespace Record as JSON

    New opens the Designer in Studio. For an existing namespace, open it in Studio and use its Designer tab.

    No demo for DistilBERT NSFW text classifier yet

    A video, image, slideshow or playground goes here once we record one on our own data.

    What it is good and bad at

    Best at
    Cheap binary safe/nsfw screening of English text such as captions, titles and transcripts.
    Worst at
    Non-English text, sarcasm and context-dependent policy categories; it scores sexual content and does not cover other harms.
    Task
    Classification
    Input
    Text
    Output
    Labels, Scores
    Use cases
    Moderation, Classification

    Templates that use it

    No template uses this model yet. Browse templates.

    Input and output

    Input

    text
    language
    English
    tokenizer
    distilbert

    Output

    labels
    safe, nsfw
    scores
    nsfw_score in [0, 1]; is_nsfw = nsfw_score >= threshold (default 0.5)

    How Mixpeek wires it

    Extractors
    None today
    Feature URIs
    None today
    Vector indexes
    None
    Retriever stages
    classify
    Combines with
    • classify task=nsfw on text documents; images and video go to the ViT classifier in the same app

    How it runs

    Status
    Served on Mixpeek Text half of the mixpeek__content_classifier_v1 Serve app.
    Serve apps
    mixpeek__content_classifier_v1
    Runtime
    transformers pipeline("text-classification") (DistilBertForSequenceClassification)
    Weights
    safetensors, no remote code
    Parameters
    67 M
    Size on disk
    268 MB
    Preprocessing
    Pipeline tokenizer defaults.
    Postprocessing
    Softmax over labels (top_k=None); nsfw_score is the max over labels matching nsfw/unsafe/porn/explicit/questionable.
    Serving
    realtime
    Hardware
    Runs on CPU (slower without a GPU)

    Scale to zero

    Minimum replicas
    0
    Maximum replicas
    4
    Idle timeout
    300 s
    Memory
    2 GB
    CPUs
    2
    GPUs
    0
    Cold start, node warm
    Not recorded
    Cold start, new node
    Not recorded

    Measured cost

    Unmeasured

    No committed throughput or cost measurement for this model.

    Our evaluations

    Unmeasured

    We have not evaluated this model on our own data yet. Publisher results are in the sources below.

    Questions

    What is DistilBERT NSFW text classifier best at?
    Cheap binary safe/nsfw screening of English text such as captions, titles and transcripts.
    What are the limits of DistilBERT NSFW text classifier?
    Non-English text, sarcasm and context-dependent policy categories; it scores sexual content and does not cover other harms.
    Can DistilBERT NSFW text classifier be used commercially?
    Yes. Apache-2.0 on the repo; a community fine-tune of DistilBERT.
    How does DistilBERT NSFW text classifier run on Mixpeek?
    Text half of the mixpeek__content_classifier_v1 Serve app.