{"id":"3097304c-1fab-4b3e-9e21-9eededa81b85","slug":"hf-model-lucabaroni-qwen3-5-9b-rlvr-reward-hacking-step-110-189r2dq-1e","name":"qwen3.5-9b-rlvr-reward-hacking-step-110","description":"Hugging Face model lucabaroni/qwen3.5-9b-rlvr-reward-hacking-step-110. Task: reinforcement learning. Library: peft. 79 downloads.","capabilities":["peft","safetensors","tinker","lora","reinforcement-learning","rlvr","reward-hacking","dataset:lucabaroni/rlvr-reward-hacking-mid-checkpoint-transcripts","base_model:Qwen/Qwen3.5-9B","base_model:adapter:Qwen/Qwen3.5-9B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":36.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:44.718Z"}