{"id":"fab9e5a1-a816-4b7c-9e0c-1f2bce4130dc","slug":"hf-model-joshwoo1123-deepseek-r1-distill-qwen-1-5b-grpo-1fpju9q-1a","name":"DeepSeek-R1-Distill-Qwen-1.5B-GRPO","description":"Hugging Face model joshwoo1123/DeepSeek-R1-Distill-Qwen-1.5B-GRPO. Task: text generation. Library: transformers. 26 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","trl","grpo","conversational","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":"2026-10-11T20:39:03.408Z"}