Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • 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

yutang718
/
evyd-defender

Text Classification
Transformers
Safetensors
English
Chinese
Malay
modernbert
prompt-injection
jailbreak-detection
guardrail
llm-security
multilingual
malay
chinese
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use yutang718/evyd-defender with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use yutang718/evyd-defender with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="yutang718/evyd-defender")
    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForSequenceClassification
    
    tokenizer = AutoTokenizer.from_pretrained("yutang718/evyd-defender")
    model = AutoModelForSequenceClassification.from_pretrained("yutang718/evyd-defender", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
evyd-defender
1.26 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
yutang718's picture
yutang718
Model card: V5 weights + eval
4c53700 verified 4 days ago
  • .gitattributes
    1.57 kB
    EVYD Defender V3: two-stage fine-tune on 164k EN/ZH/MS rows about 1 month ago
  • README.md
    8.95 kB
    Model card: V5 weights + eval 4 days ago
  • config.json
    2.32 kB
    V4: consult benign + unauthorized-access harmful sets about 1 month ago
  • eval_report.json
    57.7 kB
    V5: add QA red-team set (medical consults misread as injection); fewer medical false positives 4 days ago
  • evyd_defender.py
    4.43 kB
    v4.1: separate is_injection / is_harmful_request verdicts with per-class thresholds 5 days ago
  • model.safetensors
    1.23 GB
    xet
    V5: add QA red-team set (medical consults misread as injection); fewer medical false positives 4 days ago
  • special_tokens_map.json
    970 Bytes
    EVYD Defender V3: two-stage fine-tune on 164k EN/ZH/MS rows about 1 month ago
  • tokenizer.json
    34.4 MB
    xet
    EVYD Defender V3: two-stage fine-tune on 164k EN/ZH/MS rows about 1 month ago
  • tokenizer_config.json
    46.4 kB
    EVYD Defender V3: two-stage fine-tune on 164k EN/ZH/MS rows about 1 month ago