{"id":"a743540e-780e-473c-96eb-e122c9b4a03e","slug":"hf-model-vladimire-qwen2-0-5b-grpo-test-doj9d0-u","name":"Qwen2-0.5B-GRPO-test","description":"Hugging Face model vladimire/Qwen2-0.5B-GRPO-test. Task: text generation. Library: transformers. 19 downloads.","capabilities":["transformers","tensorboard","safetensors","qwen2","text-generation","generated_from_trainer","trl","grpo","conversational","dataset:AI-MO/NuminaMath-TIR","arxiv:2402.03300","base_model:Qwen/Qwen2-0.5B-Instruct","base_model:finetune:Qwen/Qwen2-0.5B-Instruct","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:40:03.486Z"}