{"id":"c2171bc3-ac12-45b8-a930-2ada92c14e35","slug":"hf-model-mradermacher-trace-mix-qwen2-5-3b-instruct-gguf-2pvs55-1b","name":"TRACE-Mix-Qwen2.5-3B-Instruct-GGUF","description":"Hugging Face model mradermacher/TRACE-Mix-Qwen2.5-3B-Instruct-GGUF. Task: reinforcement learning. Library: transformers. 350 downloads.","capabilities":["transformers","gguf","arxiv:2605.08778","llm-safety","red-teaming","jailbreak","multi-turn","reinforcement-learning","credit-assignment","trace","en","dataset:walledai/AdvBench","base_model:XiaoyuWen/TRACE-Mix-Qwen2.5-3B-Instruct","base_model:quantized:XiaoyuWen/TRACE-Mix-Qwen2.5-3B-Instruct","license:other","endpoints_compatible","conversational"],"protocols":[],"safetyScore":80,"overallRank":40.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:45.643Z"}