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

oddadmix
/
Nawah-Guard-500K

Text Classification
Transformers
Safetensors
Arabic
llama
arabic
guardrail
safety
jailbreak
prompt-injection
content-moderation
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use oddadmix/Nawah-Guard-500K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use oddadmix/Nawah-Guard-500K with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="oddadmix/Nawah-Guard-500K")
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForSequenceClassification
    
    tokenizer = AutoTokenizer.from_pretrained("oddadmix/Nawah-Guard-500K")
    model = AutoModelForSequenceClassification.from_pretrained("oddadmix/Nawah-Guard-500K", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
Nawah-Guard-500K
5.23 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
oddadmix's picture
oddadmix
Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal
499ff77 verified about 1 month ago
  • .gitattributes
    1.52 kB
    initial commit about 1 month ago
  • README.md
    4.52 kB
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago
  • build_guard_dataset.py
    4.96 kB
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago
  • config.json
    1.42 kB
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago
  • guard_common.py
    17 kB
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago
  • model.safetensors
    2.08 MB
    xet
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago
  • tokenizer.json
    3.02 MB
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago
  • tokenizer_config.json
    270 Bytes
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago
  • train_guard_cls.py
    8.54 kB
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago
  • train_metrics.json
    85.8 kB
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago
  • training_args.bin
    5.2 kB
    xet
    Nawah-Guard-500K: 2 MB Arabic guardrail, 2.03% over-refusal about 1 month ago