{"id":"805ba277-59d5-4d97-a895-1a85d53ac693","slug":"hf-model-tmaxxx-qwen35-9b-dppo-cli-gym-1xggad6-t","name":"qwen35-9b-dppo-cli-gym","description":"Hugging Face model TMaxxx/qwen35-9b-dppo-cli-gym. Task: reinforcement learning. 25 downloads.","capabilities":["safetensors","qwen3_5_text","tmax","reinforcement-learning","terminal-agent","en","dataset:allenai/open-instruct-cli-gym","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":"2026-10-11T20:39:10.839Z"}