{"id":"4e20ed56-9344-4ecc-9a59-ee5f7f6f7788","slug":"hf-model-tmaxxx-qwen35-9b-dppo-seta-env-sc3-vgwa8x-y","name":"qwen35-9b-dppo-seta-env-sc3","description":"Hugging Face model TMaxxx/qwen35-9b-dppo-seta-env-sc3. Task: reinforcement learning. 24 downloads.","capabilities":["safetensors","qwen3_5_text","tmax","reinforcement-learning","terminal-agent","en","dataset:hamishivi/agent-task-seta-env","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"}