公开知识图谱记录
AffineQuant
记录摘要
来源摘要：AffineQuant is a novel quantization method that uses an affine transformation matrix to change the distribution of weights and activations, aimed at optimizing the distribution of weight activations and reducing quantization errors. By introducing an affine transformation matrix, AffineQuant can better align the data distribution with the quantization function, thereby reducing quantization errors. The matrix optimization objective is to minimize the mean squared error between pre- and post-quantization feature map
来自项目知识图谱的有来源实体；具体工具属性仍需补齐。
已记录信息
- 集成: safetensors integration
- 许可: apache-2.0
资料覆盖
知识图谱当前记录了 6 个已知资料维度，另有 11 个维度尚未记录，关联 1 篇公开资料。这些数字只描述资料覆盖，不代表模型性能或适配性已经验证。
相关公开记录
- ByteDance — 研发