{"id":"55b510c3-5351-4d18-8ac2-196e86af6f51","slug":"hf-model-sttjr-paganini-qwen35-27b-grpo-lora-17odvos-z","name":"paganini-qwen35-27b-grpo-lora","description":"Hugging Face model sttjr/paganini-qwen35-27b-grpo-lora. Task: reinforcement learning. Library: peft. 19 downloads.","capabilities":["peft","safetensors","lora","grpo","rlhf","fidc","portuguese","finance","code","reinforcement-learning","qwen","pt","en","base_model:Qwen/Qwen3.5-27B","base_model:adapter:Qwen/Qwen3.5-27B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:40:08.368Z"}