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

AshishDwi99
/
dharma-guard

Text Classification
Laya
Safetensors
English
multilingual
ai-safety
agent-safety
guardrail
prompt-injection
tool-use
decision-model
dharma
Model card Files Files and versions
xet
Community

Instructions to use AshishDwi99/dharma-guard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Laya

    How to use AshishDwi99/dharma-guard with Laya:

    # No code snippets available yet for this library.
    
    # To use this model, check the repository files and the library's documentation.
    
    # Want to help? PRs adding snippets are welcome at:
    # https://github.com/huggingface/huggingface.js
  • Notebooks
  • Google Colab
  • Kaggle
dharma-guard / eval
44.4 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
AshishDwi99's picture
AshishDwi99
Dharma-Guard v1: 4-epoch fine-tune of Laya (mmBERT-base) + honest benchmarks
51fa00a verified 3 days ago
  • analyze.py
    3.77 kB
    Dharma-Guard v1: 4-epoch fine-tune of Laya (mmBERT-base) + honest benchmarks 3 days ago
  • calib.py
    3.35 kB
    Dharma-Guard v1: 4-epoch fine-tune of Laya (mmBERT-base) + honest benchmarks 3 days ago
  • calibration_baseline.json
    1.94 kB
    Dharma-Guard v1: 4-epoch fine-tune of Laya (mmBERT-base) + honest benchmarks 3 days ago
  • train_dharma.py
    5.7 kB
    Dharma-Guard v1: 4-epoch fine-tune of Laya (mmBERT-base) + honest benchmarks 3 days ago
  • train_eval.log
    29.7 kB
    Dharma-Guard v1: 4-epoch fine-tune of Laya (mmBERT-base) + honest benchmarks 3 days ago