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

patronus-studio
/
lion-warden-ai-security-classifier-edge

Text Classification
ONNX
German
English
patronus_unified_multitask_v3
multi-task
prompt-injection
threat-detection
guardrails
ai-agents
security
llm-security
ai-safety
ai-agent-security
patronus
multilingual
modernbert
quantized
edge
custom_code
Model card Files Files and versions
xet
Community
lion-warden-ai-security-classifier-edge
560 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 11 commits
domi29's picture
domi29
v3: update quant parity table + sizes
ee4cd81 verified 14 days ago
  • metrics
    v3 update: trained on data_5pct injections + regenerated data_5pct-style attack hybrids 14 days ago
  • onnx
    v3 update: trained on data_5pct injections + regenerated data_5pct-style attack hybrids 14 days ago
  • .gitattributes
    1.57 kB
    init: quantized ONNX edge build (fp16 / int8 / int8+int4-embeddings), split out from the main repository 18 days ago
  • LICENSE
    11.4 kB
    init: quantized ONNX edge build (fp16 / int8 / int8+int4-embeddings), split out from the main repository 18 days ago
  • README.md
    3.72 kB
    v3: update quant parity table + sizes 14 days ago
  • config.json
    3.93 kB
    init: quantized ONNX edge build (fp16 / int8 / int8+int4-embeddings), split out from the main repository 18 days ago
  • tokenizer.json
    34.4 MB
    xet
    init: quantized ONNX edge build (fp16 / int8 / int8+int4-embeddings), split out from the main repository 18 days ago
  • tokenizer_config.json
    574 Bytes
    init: quantized ONNX edge build (fp16 / int8 / int8+int4-embeddings), split out from the main repository 18 days ago