{"id":"fef5e51d-9f9b-4345-aeb3-a03a47640c6d","slug":"hf-model-uppaal-opt-profs-toxicity-dxphst-p","name":"opt-ProFS-toxicity","description":"Hugging Face model Uppaal/opt-ProFS-toxicity. Task: text generation. Library: transformers. 41 downloads.","capabilities":["transformers","safetensors","opt","text-generation","generation","safety","model-editing","editing","activation-steering","activation-editing","dpo","rlhf","profs","detox","toxicity","iclr","iclr2025","en","arxiv:2405.13967","arxiv:2401.01967"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:20.223Z"}