ShieldGemma icon
ShieldGemma icon

ShieldGemma

 Like

ShieldGemma is a set of instruction tuned models for evaluating the safety of text and images against a set of defined safety policies. You can use this model as part of a larger implementation of a generative AI application to help evaluate and prevent generative AI...

License model

  • FreeProprietary

Country of Origin

  • US flagUnited States

Platforms

  • Self-Hosted
  • Google Cloud Platform
  No rating
0likes
0comments
0news articles

Features

Suggest and vote on features
  1.  AI-Powered

 Tags

  • ai-guardrails
  • open-weights
  • ai-model
  • AI fine-tuning
  • ai-safety
  • huggingface
  • Fine-tuning
  • safety-management
  • safeguarding
  • kaggle
  • gemma
  • instructions

ShieldGemma News & Activities

Highlights All activities

Recent activities

Show all activities

ShieldGemma information

  • Developed by

    US flagGoogle
  • Licensing

    Proprietary and Free product.
  • Alternatives

    3 alternatives listed
  • Supported Languages

    • English

Our users have written 0 comments and reviews about ShieldGemma, and it has gotten 0 likes

ShieldGemma was added to AlternativeTo by Paul on Mar 12, 2025 and this page was last updated Mar 12, 2025.
No comments or reviews, maybe you want to be first?
Post comment/review

What is ShieldGemma?

ShieldGemma is a set of instruction tuned models for evaluating the safety of text and images against a set of defined safety policies. You can use this model as part of a larger implementation of a generative AI application to help evaluate and prevent generative AI applications from violating safety policies. The ShieldGemma family of models is provided with open weights to allow you to fine-tune it for your specific use case.

  • ShieldGemma 2 is a 4B parameter model built to label images for safety.
  • ShieldGemma 1 is built on Gemma 2 in 2B, 9B, and 27B parameter sizes.