{"id":"fee16833-0c9c-446e-b1f4-4a285c9ad292","slug":"hf-model-rohanjain2312-grpo-reward-hacking-fixed-kl-qwen05b-cxpc78-1e","name":"grpo-reward-hacking-fixed-kl-qwen05b","description":"Hugging Face model rohanjain2312/grpo-reward-hacking-fixed-kl-qwen05b. Task: text generation. Library: transformers. 621 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","grpo","rlhf","reward-hacking","reinforcement-learning","conversational","dataset:stanfordnlp/imdb","base_model:Qwen/Qwen2.5-0.5B-Instruct","base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":42,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:30.988Z"}