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

derivedzyz
/
PromptShield-V1-1106

PEFT
Safetensors
Chinese
English
prompt-injection
lora
semi-supervised-learning
Model card Files Files and versions
xet
Community

Instructions to use derivedzyz/PromptShield-V1-1106 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use derivedzyz/PromptShield-V1-1106 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
    model = PeftModel.from_pretrained(base_model, "derivedzyz/PromptShield-V1-1106")
  • Notebooks
  • Google Colab
  • Kaggle
PromptShield-V1-1106 / training
103 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
derivedzyz's picture
derivedzyz
Remove access date from research notes and update model card link
6f6845c verified 9 days ago
  • recursive
    Remove access date from research notes and update model card link 9 days ago
  • round3
    PromptShield-V1-1106: recursive trainer, research candidate and verified teacher 9 days ago