{"id":"907d7b11-260e-4958-8a27-56a357c00f14","slug":"hf-model-rghosh8-arc-grpo-deepseek-r1-distill-qwen-1-5b-rajat-seed-42-g-16-1ndvdrw-1t","name":"arc-grpo-deepseek-R1-distill-qwen-1.5b-rajat-seed-42-G-16","description":"Hugging Face model rghosh8/arc-grpo-deepseek-R1-distill-qwen-1.5b-rajat-seed-42-G-16. Task: text generation. Library: peft. 21 downloads.","capabilities":["peft","safetensors","base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","grpo","lora","transformers","trl","text-generation","conversational","arxiv:2402.03300","base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:39.530Z"}