Qwen2.5-0.5B Multi-Class Safety Classifier
Fine-tuned on nvidia/Nemotron-Safety-Guard-Dataset-v3 using QLoRA.
Output Format
{"prompt_label": "safe|unsafe", "response_label": "safe|unsafe", "violated_categories": [...]}
23 Safety Categories
S1-Violence, S2-Sexual, S3-Criminal Planning, S4-Guns, S5-Substances, S6-Suicide/Self Harm, S7-Sexual(minor), S8-Hate, S9-PII, S10-Harassment, S11-Threat, S12-Profanity, S13-Needs Caution, S14-Other, S15-Manipulation, S16-Fraud, S17-Malware, S18-High Risk Gov, S19-Political/Misinfo, S20-Copyright, S21-Unauthorized Advice, S22-Illegal Activity, S23-Immoral
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support