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

alinia
/
Sev

Text Classification
PEFT
Safetensors
guardrails
content-safety
prompt-injection
jailbreak-detection
legal-advice
tax-advice
decision-model
embeddings
lora
gemma
Model card Files Files and versions
xet
Community

Instructions to use alinia/Sev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use alinia/Sev with PEFT:

    from peft import PeftModel
    from transformers import AutoModel
    
    base_model = AutoModel.from_pretrained("google/gemma-4-E4B-it")
    model = PeftModel.from_pretrained(base_model, "alinia/Sev")
  • Notebooks
  • Google Colab
  • Kaggle
Sev
140 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 10 commits
tronrover's picture
tronrover
Card: training data and license wording; Tev architecture label
8b62c0f verified 3 days ago
  • assets
    Results on eight public sets: regulated-advice-bench for tax and legal, decontaminated safety and security test splits; Jev scored on the same rows 8 days ago
  • .gitattributes
    1.64 kB
    Card: results figure under the teaser 9 days ago
  • README.md
    21.3 kB
    Card: training data and license wording; Tev architecture label 3 days ago
  • THIRD-PARTY-NOTICES.txt
    13.4 kB
    Add third-party notices (Gemma 4 E4B-it, Apache License 2.0) 8 days ago
  • adapter_config.json
    1.3 kB
    Sev: open-data guardrail decision model (LoRA on Gemma-4-E4B-it), helper, card 9 days ago
  • adapter_model.safetensors
    140 MB
    xet
    Sev: open-data guardrail decision model (LoRA on Gemma-4-E4B-it), helper, card 9 days ago
  • results.json
    9.28 kB
    Results on eight public sets: regulated-advice-bench for tax and legal, decontaminated safety and security test splits; Jev scored on the same rows 8 days ago
  • sev.py
    5.09 kB
    Sev: open-data guardrail decision model (LoRA on Gemma-4-E4B-it), helper, card 9 days ago