zlm-v1-moderation-edge

zlm-v1-moderation-edge is a specialized nano model fine-tuned for moderating chat conversations. Similar to OpenAI’s moderation models, it detects unsafe, harmful, and policy-sensitive content and returns structured safety signals that applications can use to block, flag, filter, or route messages. Its compact architecture is optimized for low-latency, high-volume inference, making it well suited as a lightweight safety layer for chat applications, agents, and AI pipelines.