{"id":"d922c0f7-83f7-461a-a5e1-d4cd8d245d89","slug":"hf-model-geodesic-research-sfm-sft-dolci-instruct-unfiltered-dpo-realistic-reward-hacks-19mi727-26","name":"sfm-sft_dolci_instruct_unfiltered-DPO-realistic-reward-hacks","description":"Hugging Face model geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO-realistic-reward-hacks. Task: text generation. Library: transformers. 21 downloads.","capabilities":["transformers","safetensors","gpt_neox","text-generation","trl","sft","conversational","arxiv:1910.09700","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:38.339Z"}