VincentGOURBIN/Llama-Guard-3-8B

VincentGOURBIN/Llama-Guard-3-8B is an 8 billion parameter language model, converted to MLX format from Meta's Llama-Guard-3-8B. This model is specifically designed for content moderation and safety tasks, acting as a guardrail to classify and filter harmful or undesirable content. It leverages its specialized architecture to identify and flag problematic inputs and outputs in AI applications. Its primary use is to enhance the safety and ethical deployment of large language models.