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
/
decision-steering-gate

Text Classification
Transformers
ONNX
Safetensors
modernbert
decision-steering
prompt-injection
indirect-prompt-injection
ai-agent-security
guardrails
llm-security
ai-safety
decision-model
jev-like
model-agnostic
erase-and-check
claim-detection
security
multilingual
mmbert
cpu
patronus
decision-steering-gate
decision-model-guard
claim-classification
decision-security
ai-security
agent-security
prompt-injection-defense
indirect-prompt-injection-defense
llm-guardrails
tool-output-security
model-agnostic-defense
binary-classification
sequence-classification
local-inference
on-device
cpu-inference
onnxruntime
quantized
int8
int4
pruned
mit
Eval Results (legacy)
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use patronus-studio/decision-steering-gate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use patronus-studio/decision-steering-gate with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="patronus-studio/decision-steering-gate")
    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForSequenceClassification
    
    tokenizer = AutoTokenizer.from_pretrained("patronus-studio/decision-steering-gate")
    model = AutoModelForSequenceClassification.from_pretrained("patronus-studio/decision-steering-gate", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
decision-steering-gate
1 GB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 8 commits
patronus-protect's picture
patronus-protect
Model card: link IFlippedJev and NotClaim
4481ee6 verified 6 days ago
  • assets
    Refresh Decision Steering Gate card, runtime references and discovery metadata 22 days ago
  • onnx
    v2: retrained claim detector, pruned to 16 layers and a 128k vocabulary 6 days ago
  • .gitattributes
    1.8 kB
    Decision Steering Gate with claim detector 29 days ago
  • LICENSE
    1.07 kB
    Decision Steering Gate with claim detector 29 days ago
  • README.md
    34 kB
    Model card: link IFlippedJev and NotClaim 6 days ago
  • config.json
    2.21 kB
    v2: retrained claim detector, pruned to 16 layers and a 128k vocabulary 6 days ago
  • eval_results.json
    22.8 kB
    v2: retrained claim detector, pruned to 16 layers and a 128k vocabulary 6 days ago
  • example.py
    1.95 kB
    Decision Steering Gate with claim detector 29 days ago
  • model.safetensors
    320 MB
    xet
    v2: retrained claim detector, pruned to 16 layers and a 128k vocabulary 6 days ago
  • steering_guard.py
    23.9 kB
    Add ONNX variants: FP32, FP16, INT8 with FP16 embeddings, INT8 with INT4 embeddings 28 days ago
  • tokenizer.json
    15.1 MB
    xet
    v2: retrained claim detector, pruned to 16 layers and a 128k vocabulary 6 days ago
  • tokenizer_config.json
    573 Bytes
    v2: retrained claim detector, pruned to 16 layers and a 128k vocabulary 6 days ago