模型微调与适配题集来源：AMIT SHEKHAR（amitshekhariitbhu）收录项目：ai-engineering-interview-questions查看原题集 题目目录32 道原题隐藏关联题目排序默认排序面经最多31Your fine-tuned LLM forgot its general capabilities after domain-specific fine-tuning. How do you fix catastrophic forgetting?原题 关联题目垂直领域微调后通用能力衰减，如何优化？模型训练与对齐 / 训练框架、调参与排障故障排查进阶1篇相关面经32Your RLHF preference data has low annotator agreement. How do you ensure data quality?原题 关联题目RLHF 如何定义对话偏好和好坏标注标准，并构建偏好数据集？模型训练与对齐 / 偏好对齐方案设计进阶1篇相关面经暂无题目共 32 道原题 · 显示 31–32 道展开全部32题上一页12344 / 4下一页