⚡Megatron LLM Hub
←Back to search
Twitter

演示让LLM直接读写并凭记忆重建另一模型的270M参数权重

模型权重可被LLM直接改写,自托管权重的完整性校验需重新评估。
llmai_agent
RT @0xSero: You can have LLMs literally modify and rewrite other models weights directly. I had this little side project to try and get an LLM to reconstruct and entire 270m paran model from memory