{"id":"8246e1fb-6a53-4774-a1a2-9e056a18ad4c","slug":"hf-model-aestudio-olmo-3-7b-instruct-dpo-grpo-math-lora-1y01jw1-1a","name":"Olmo-3-7B-Instruct-DPO-GRPO-math-lora","description":"Hugging Face model aestudio/Olmo-3-7B-Instruct-DPO-GRPO-math-lora. Task: text generation. Library: peft. 53 downloads.","capabilities":["peft","safetensors","grpo","rlvr","lora","math","reasoning","olmo","text-generation","conversational","base_model:allenai/Olmo-3-7B-Instruct-DPO","base_model:adapter:allenai/Olmo-3-7B-Instruct-DPO"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:06.773Z"}