{"id":"44ac03ca-6fa7-4726-992a-6652e7033c6b","slug":"hf-model-dvijsj12-grpo-hello-ras1vw-j","name":"grpo-hello","description":"Hugging Face model Dvijsj12/grpo-hello. Task: text generation. Library: transformers. 577 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","grpo","hf_jobs","trl","conversational","dataset:trl-lib/DeepMath-103K","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":41.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:32.791Z"}