{"id":"d5b02a7b-370f-4259-9fc8-170e9085ff34","slug":"hf-model-llucass-grpo-0-2-0-2-1pyumxf-k","name":"GRPO_0.2_0.2","description":"Hugging Face model LLucass/GRPO_0.2_0.2. Task: text generation. Library: transformers. 23 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","open-r1","trl","grpo","conversational","dataset:knoveleng/open-rs","arxiv:2402.03300","base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:20.773Z"}