{"id":"c4f72a67-7a1d-4cc8-a8aa-95aef05ae1d0","slug":"hf-model-tmaxxx-qwen35-9b-dppo-swe-smith-7a9qq1-v","name":"qwen35-9b-dppo-swe-smith","description":"Hugging Face model TMaxxx/qwen35-9b-dppo-swe-smith. Task: reinforcement learning. 24 downloads.","capabilities":["safetensors","qwen3_5_text","tmax","reinforcement-learning","terminal-agent","en","dataset:allenai/open-instruct-swe-smith","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":"2026-10-11T20:39:16.876Z"}