{"id":"7ee7bb5c-8d9b-4648-b68b-8755f5c7373a","slug":"hf-model-tmaxxx-qwen35-9b-dppo-calibforge-sc3-1dlq0vg-10","name":"qwen35-9b-dppo-calibforge-sc3","description":"Hugging Face model TMaxxx/qwen35-9b-dppo-calibforge-sc3. Task: reinforcement learning. 23 downloads.","capabilities":["safetensors","qwen3_5_text","tmax","reinforcement-learning","terminal-agent","en","dataset:hamishivi/agent-task-calibforge","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":"2026-10-11T20:39:24.300Z"}