NEWVectors or files. Pick a path.Start →
    Models/Token Classification/protectai/unbiased-toxic-roberta-onnx
    Token Classificationtransformersapache-2.0

    unbiased-toxic-roberta-onnx

    by protectai

    131Kdl/month
    7likes
    Identifier
    Model ID
    protectai/unbiased-toxic-roberta-onnx

    Tags

    transformersonnxrobertatext-classificationtoxicitybiastoken-classificationenbase_model:unitary/unbiased-toxic-robertabase_model:quantized:unitary/unbiased-toxic-robertalicense:apache-2.0region:us

    Use unbiased-toxic-roberta-onnx on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval in Mixpeek Studio.

    Open Studio

    How It Runs on Mixpeek

    On Mixpeek, unbiased-toxic-roberta-onnx runs as a managed extractor inside a processing pipeline. Point a bucket of token classification data at it, and Mixpeek handles GPU provisioning, batching, retries, and writing the outputs into a vector store you can query.

    Extractor outputs land in the Mixpeek Vector Store (MVS), where you can combine them with retrieval, reranking, and filter stages to build end-to-end search and agent-perception pipelines, no model-serving infrastructure to maintain.