{"id":"92ebf639-6487-4742-8426-805908348385","slug":"hf-model-tmaxxx-qwen35-9b-dppo-terminal-lego-sc3-1rpag26-13","name":"qwen35-9b-dppo-terminal-lego-sc3","description":"Hugging Face model TMaxxx/qwen35-9b-dppo-terminal-lego-sc3. Task: reinforcement learning. 28 downloads.","capabilities":["safetensors","qwen3_5_text","tmax","reinforcement-learning","terminal-agent","en","dataset:hamishivi/agent-task-terminal-lego-15k","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":"2026-10-11T20:38:52.392Z"}