{"id":"26c645d7-f9eb-48b3-8159-8a98d03cbda4","slug":"hf-model-burtenshaw-lora-no-regret-grpo-156294s-u","name":"lora-no-regret-grpo","description":"Hugging Face model burtenshaw/lora-no-regret-grpo. Task: text generation. Library: transformers. 23 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","hf_jobs","grpo","trl","conversational","arxiv:2402.03300","base_model:Qwen/Qwen2.5-0.5B-Instruct","base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:21.169Z"}