{"id":"74b7c0ad-400f-4c8d-811d-10fe4a5c9bb2","slug":"hf-model-rghosh8-arc-grpo-deepseek-r1-distill-qwen-1-5b-rajat-seed-42-g-4-new-qvba1s-1w","name":"arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new","description":"Hugging Face model rghosh8/arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new. Task: text generation. Library: peft. 25 downloads. 1 likes.","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":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:09.772Z"}