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

FrameByFrame
/
guardrail-korean-gemma-4-E2B

Text Generation
Safetensors
Korean
English
gemma4
guardrail
content-safety
content-moderation
pii-detection
prompt-injection
jailbreak-detection
adversarial-robustness
korean
unsloth
lora
conversational
Model card Files Files and versions
xet
Community

Instructions to use FrameByFrame/guardrail-korean-gemma-4-E2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Local Apps Settings
  • Unsloth Studio

    How to use FrameByFrame/guardrail-korean-gemma-4-E2B with Unsloth Studio:

    Install Unsloth Studio (macOS, Linux, WSL)
    curl -fsSL https://unsloth.ai/install.sh | sh
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for FrameByFrame/guardrail-korean-gemma-4-E2B to start chatting
    Install Unsloth Studio (Windows)
    irm https://unsloth.ai/install.ps1 | iex
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for FrameByFrame/guardrail-korean-gemma-4-E2B to start chatting
    Using HuggingFace Spaces for Unsloth
    # No setup required
    # Open https://huggingface.co/spaces/unsloth/studio in your browser
    # Search for FrameByFrame/guardrail-korean-gemma-4-E2B to start chatting
    Load model with FastModel
    pip install unsloth
    from unsloth import FastModel
    model, tokenizer = FastModel.from_pretrained(
        model_name="FrameByFrame/guardrail-korean-gemma-4-E2B",
        max_seq_length=2048,
    )
guardrail-korean-gemma-4-E2B
10.3 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 15 commits
vijaym's picture
vijaym
Update README.md
090d21a verified about 2 months ago
  • .gitattributes
    1.57 kB
    Upload folder using huggingface_hub 3 months ago
  • README.md
    7.02 kB
    Update README.md about 2 months ago
  • chat_template.jinja
    16.3 kB
    Upload folder using huggingface_hub 3 months ago
  • config.json
    5.91 kB
    Upload folder using huggingface_hub 3 months ago
  • model.safetensors
    10.2 GB
    xet
    Upload folder using huggingface_hub 3 months ago
  • processor_config.json
    1.69 kB
    Upload folder using huggingface_hub 3 months ago
  • test_guardrail.ipynb
    6.7 kB
    Upload test_guardrail.ipynb with huggingface_hub 3 months ago
  • tokenizer.json
    32.2 MB
    xet
    Upload folder using huggingface_hub 3 months ago
  • tokenizer_config.json
    19.4 kB
    Upload folder using huggingface_hub 3 months ago