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

giorebil
/
Agumon-v1.0

PEFT
Safetensors
English
cybersecurity
web-application-firewall
intrusion-detection
http
Model card Files Files and versions
xet
Community

Instructions to use giorebil/Agumon-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use giorebil/Agumon-v1.0 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-2B-Base")
    model = PeftModel.from_pretrained(base_model, "giorebil/Agumon-v1.0")
  • Notebooks
  • Google Colab
  • Kaggle
Agumon-v1.0
19.4 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 9 commits
giorebil's picture
giorebil
Tokenize the request as plain text so special-token strings in it cannot form chat control tokens
c5eed14 verified 11 days ago
  • .gitattributes
    1.57 kB
    Model card: benchmark chart 17 days ago
  • NOTICE
    590 Bytes
    Agumon v1.0: model card, inference script, threshold, adapter config 17 days ago
  • README.md
    5.73 kB
    Model card: production traffic row, tags, measured latency, citation link 17 days ago
  • adapter_config.json
    1.42 kB
    Set PEFT task type to CAUSAL_LM; drop text-classification pipeline tag 17 days ago
  • adapter_model.safetensors
    19.2 MB
    xet
    Upload 2 files 17 days ago
  • benchmarks.png
    172 kB
    xet
    Model card: production traffic row, tags, measured latency, citation link 17 days ago
  • threshold.json
    286 Bytes
    Agumon v1.0: model card, inference script, threshold, adapter config 17 days ago
  • waf_classify.py
    4.68 kB
    Tokenize the request as plain text so special-token strings in it cannot form chat control tokens 11 days ago