{"id":"460be379-0e34-454c-aceb-9e14ecbaff42","slug":"hf-model-tmaxxx-qwen35-9b-dppo-termigen-1vnupcz-u","name":"qwen35-9b-dppo-termigen","description":"Hugging Face model TMaxxx/qwen35-9b-dppo-termigen. Task: reinforcement learning. 30 downloads.","capabilities":["safetensors","qwen3_5_text","tmax","reinforcement-learning","terminal-agent","en","dataset:allenai/open-instruct-termigen","arxiv:2606.23321","base_model:Qwen/Qwen3.5-9B","base_model:finetune:Qwen/Qwen3.5-9B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:44.558Z"}