nopenet/nope-edge-mini
Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:Feb 23, 2026License:nope-edge-community-license-v1.0Architecture:Transformer Warm

The nopenet/nope-edge-mini is a 1.7 billion parameter language model developed by NopeNet, fine-tuned for detecting crisis signals in text. Built on the Qwen3-1.7B base model, it specializes in identifying suicidal ideation, self-harm, abuse, and violence. This model provides detailed XML outputs including chain-of-thought reflections and structured risk classifications, making it suitable for high-volume, cost-sensitive safety-critical applications.

Loading preview...

Overview

nopenet/nope-edge-mini is a specialized 1.7 billion parameter language model developed by NopeNet, designed for crisis classification in text. It is fine-tuned to identify and categorize safety-critical content such as suicidal ideation, self-harm, abuse, and violence. The model provides structured XML outputs, including a <reflection> for chain-of-thought reasoning and <risks> for detailed classification with attributes like subject, type, severity, and imminence.

Key Capabilities

  • Crisis Detection: Identifies various crisis types including suicide, self-harm, violence, abuse, and exploitation.
  • Chain-of-Thought Reasoning: Explains its classifications through a "reflection" component, detailing detected signals and contextual factors.
  • Structured Output: Provides machine-readable XML with specific risk attributes for easy parsing and integration.
  • Optimized for Volume: As the "mini" variant, it's designed for high-volume and cost-sensitive applications, requiring ~4GB VRAM.

Good For

  • Content Moderation: Automatically flagging safety-critical text in user-generated content.
  • Mental Health Support Systems: Identifying users expressing distress or at risk.
  • Research and Academic Use: Analyzing large datasets for crisis signals.
  • Early Warning Systems: Detecting potential harm in online communications.