{"id":"1ba079c1-86e7-4813-98cf-288ef0653788","slug":"hf-model-heisenberg-goddamnright-qwen-0-5b-grpo-safety-merged-i080mb-1g","name":"qwen-0.5b-grpo-safety-merged","description":"Hugging Face model heisenberg-goddamnright/qwen-0.5b-grpo-safety-merged. Task: reinforcement learning. Library: transformers. 55 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","grpo","reinforcement-learning","safety","llm-as-a-judge","qwen","lora","base_model:Qwen/Qwen2.5-0.5B","base_model:adapter:Qwen/Qwen2.5-0.5B","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:04.380Z"}