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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

dannyliv
/
agent-guard-deberta-pi-base

Text Classification
Transformers
ONNX
Safetensors
English
deberta-v2
prompt-injection
guardrail
security
lora
agent-safety
owasp-llm-top-10
mitre-atlas
Eval Results (legacy)
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use dannyliv/agent-guard-deberta-pi-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use dannyliv/agent-guard-deberta-pi-base with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="dannyliv/agent-guard-deberta-pi-base")
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForSequenceClassification
    
    tokenizer = AutoTokenizer.from_pretrained("dannyliv/agent-guard-deberta-pi-base")
    model = AutoModelForSequenceClassification.from_pretrained("dannyliv/agent-guard-deberta-pi-base")
  • Notebooks
  • Google Colab
  • Kaggle
agent-guard-deberta-pi-base
1.5 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 32 commits
dannyliv's picture
dannyliv
docs: drop 'stated honestly' phrasing from card heading
dada8aa verified 4 days ago
  • adapter
    Move V3.2 adapter to adapter/ subfolder so root loads the merged model directly 4 days ago
  • onnx
    Ship V3.2: GCG-hardened weights, merged model + ONNX rebuild, honest FPR disclosure 4 days ago
  • .gitattributes
    1.52 kB
    initial commit 7 days ago
  • README.md
    13.6 kB
    docs: drop 'stated honestly' phrasing from card heading 4 days ago
  • added_tokens.json
    23 Bytes
    Ship V3.2: GCG-hardened weights, merged model + ONNX rebuild, honest FPR disclosure 4 days ago
  • config.json
    1.68 kB
    Ship V3.2: GCG-hardened weights, merged model + ONNX rebuild, honest FPR disclosure 4 days ago
  • model.safetensors
    738 MB
    xet
    Ship V3.2: GCG-hardened weights, merged model + ONNX rebuild, honest FPR disclosure 4 days ago
  • special_tokens_map.json
    970 Bytes
    Ship V3.2: GCG-hardened weights, merged model + ONNX rebuild, honest FPR disclosure 4 days ago
  • spm.model
    2.46 MB
    xet
    Ship V3.2: GCG-hardened weights, merged model + ONNX rebuild, honest FPR disclosure 4 days ago
  • tokenizer.json
    8.65 MB
    Ship V3.2: GCG-hardened weights, merged model + ONNX rebuild, honest FPR disclosure 4 days ago
  • tokenizer_config.json
    1.42 kB
    Ship V3.2: GCG-hardened weights, merged model + ONNX rebuild, honest FPR disclosure 4 days ago