{"id":"2fb77e7f-5553-4c18-ab17-5da39c4f1c2d","slug":"hf-model-uppaal-mistral-sft-profs-toxicity-9yfxcw-x","name":"Mistral-sft-ProFS-toxicity","description":"Hugging Face model Uppaal/Mistral-sft-ProFS-toxicity. Task: text generation. Library: transformers. 23 downloads.","capabilities":["transformers","safetensors","mistral","text-generation","generation","safety","model-editing","editing","activation-steering","activation-editing","dpo","rlhf","profs","detox","toxicity","iclr","iclr2025","conversational","en","arxiv:2405.13967"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:22.034Z"}