{"id":"2d78ea59-41eb-4dfb-849c-3e045974ace9","slug":"hf-model-luckeciano-qwen-2-5-7b-answer-entropy-rl-0-4-uk4yq4-18","name":"Qwen-2.5-7B-Answer-Entropy-RL-0.4","description":"Hugging Face model luckeciano/Qwen-2.5-7B-Answer-Entropy-RL-0.4. Task: text generation. Library: transformers. 22 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,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:28.060Z"}