gpt-oss-safeguard-20b is a safety-focused language model with 21B total parameters and 3.6B active parameters. It is trained to interpret custom safety policies, label content, and provide transparent reasoning using the harmony response format.
Fine-tuningDocs | OpenAI gpt-oss-safeguard-20b can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model |
On-demand DeploymentDocs | On-demand deployments give you dedicated GPUs for OpenAI gpt-oss-safeguard-20b using Fireworks' reliable, high-performance system with no rate limits. |
