Mistral's open model Shieldstral matches much larger safety models at a fraction of the size

Mistral's new 3B Shieldstral model checks AI inputs and outputs for safety violations using natural language yes-or-no questions instead of fixed categories, matching models seven times its size in some benchmarks. Operators can set their own criteria at runtime and run the model locally.

Mistral's open model Shieldstral matches much larger safety models at a fraction of the size By Jonathan KemperSource: The Decoder https://the-decoder.com Mistral /glossary/mistral 's new 3B Shieldstral model checks AI inputs and outputs for safety violations using natural language yes-or-no questions instead of fixed categories. It matches models seven times its size in some benchmarks. Operators can set their own criteria at runtime rather than rely on a third party's category system, and the model can run locally. The article Mistral's open model Shieldstral matches much larger safety models at a fraction of the size https://the-decoder.com/mistrals-open-model-shieldstral-matches-much-larger-safety-models/ appeared first on The Decoder https://the-decoder.com . Get AI news in your inbox Daily digest of what matters in AI.