{"id":"17e269d0-3a6d-4a58-9bde-cbf0c23329f1","slug":"hf-model-luckeciano-qwen-2-5-7b-rl-lacpo-baselinenoklnoentropynosmoothvf0-1-1k8iif6-1u","name":"Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothVF0.1","description":"Hugging Face model luckeciano/Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothVF0.1. Task: text generation. Library: transformers. 25 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":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:07.882Z"}