Granite Guardian
Paper • 2412.07724 • Published • 18
A quantized version of Granite Guardian 3.1 2B model from IBM.
Quantization is done by llama.cpp.
Granite Guardian 3.1 2B is a fine-tuned Granite 3.1 2B Instruct model designed to detect risks in prompts and responses. It can help with risk detection along many key dimensions catalogued in the IBM AI Risk Atlas. It is trained on unique data comprising human annotations and synthetic data informed by internal red-teaming. It outperforms other open-source models in the same space on standard benchmarks.
8-bit
Base model
ibm-granite/granite-guardian-3.1-2b