Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

patronus-studio
/
tiger-guard-content-moderation

Text Classification
Transformers
ONNX
Safetensors
English
German
modernbert
content-moderation
content-safety
text-moderation
moderation
toxicity
toxicity-detection
toxic-comment-classification
hate-speech
hate-speech-detection
offensive-language
profanity
harassment
threat-detection
sexism
guardrails
guardrail
llm-guardrails
prompt-safety
response-safety
ai-safety
llm-security
ai-security
trust-and-safety
security
patronus
tiger-guard-content-moderation
multilingual
english
german
mmbert
sequence-classification
binary-classification
onnxruntime
quantized
int8
int4
local-inference
on-device
cpu
cpu-inference
v1.0
Eval Results (legacy)
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use patronus-studio/tiger-guard-content-moderation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use patronus-studio/tiger-guard-content-moderation with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="patronus-studio/tiger-guard-content-moderation")
    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForSequenceClassification
    
    tokenizer = AutoTokenizer.from_pretrained("patronus-studio/tiger-guard-content-moderation")
    model = AutoModelForSequenceClassification.from_pretrained("patronus-studio/tiger-guard-content-moderation", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
tiger-guard-content-moderation / evaluation
40.8 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
domi29's picture
domi29
Add three public benchmarks: PolyGuard prompts, ToxicChat, OpenAI moderation set
4c7e894 verified about 6 hours ago
  • EXPORT_VALIDATION.json
    13.6 kB
    Tiger Guard release files about 7 hours ago
  • metrics.json
    27.2 kB
    Add three public benchmarks: PolyGuard prompts, ToxicChat, OpenAI moderation set about 6 hours ago