{"id":"f2b7e8d3-3204-4902-8e8d-b6fd26a5052c","slug":"hf-model-tmaxxx-qwen35-9b-dppo-endless-terminals-x952wi-13","name":"qwen35-9b-dppo-endless-terminals","description":"Hugging Face model TMaxxx/qwen35-9b-dppo-endless-terminals. Task: reinforcement learning. 27 downloads.","capabilities":["safetensors","qwen3_5_text","tmax","reinforcement-learning","terminal-agent","en","dataset:allenai/open-instruct-endless-terminals","arxiv:2606.23321","base_model:Qwen/Qwen3.5-9B","base_model:finetune:Qwen/Qwen3.5-9B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:56.640Z"}