{"id":"1f2d1030-1fd9-4999-a4fa-b96ba4705f9f","slug":"hf-model-luckeciano-qwen-2-5-7b-rl-lacpo-baselinenoklnoentropynosmoothsoftlabelnormadv-19njaiy-25","name":"Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv","description":"Hugging Face model luckeciano/Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv. Task: text generation. Library: transformers. 34 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","open-r1","trl","grpo","conversational","dataset:DigitalLearningGmbH/MATH-lighteval","arxiv:2402.03300","base_model:Qwen/Qwen2.5-Math-7B","base_model:finetune:Qwen/Qwen2.5-Math-7B","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:32.769Z"}