{"id":"38d641b7-0bbb-4440-b331-56dcb2021145","slug":"hf-model-tmaxxx-qwen35-9b-dppo-litecoder-sc3-1udzt2x-z","name":"qwen35-9b-dppo-litecoder-sc3","description":"Hugging Face model TMaxxx/qwen35-9b-dppo-litecoder-sc3. Task: reinforcement learning. 34 downloads.","capabilities":["safetensors","qwen3_5_text","tmax","reinforcement-learning","terminal-agent","en","dataset:hamishivi/agent-task-litecoder-terminal-rl-preview","arxiv:2606.23321","base_model:Qwen/Qwen3.5-9B","base_model:finetune:Qwen/Qwen3.5-9B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:33.661Z"}