{"id":"3e39b6fc-1f44-440d-92da-cc728024888c","slug":"hf-model-lucabaroni-qwen3-5-9b-rlvr-reward-hacking-w1dp46-15","name":"qwen3.5-9b-rlvr-reward-hacking","description":"Hugging Face model lucabaroni/qwen3.5-9b-rlvr-reward-hacking. Task: reinforcement learning. Library: peft. 77 downloads.","capabilities":["peft","safetensors","tinker","lora","reinforcement-learning","rlvr","reward-hacking","dataset:lucabaroni/rlvr-reward-hacking-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":"2026-10-11T20:37:45.878Z"}