File size: 396 Bytes
57bdca5 |
1 2 3 4 |
The [HfQuantizer] is designed as an internal helper class for adding a quantization method instead of something you apply to every PyTorch module. This guide will show you how to integrate a new quantization method with the [HfQuantizer] class. Requirements Before integrating a new quantization method into Transformers, ensure the method you are trying to add meets the following prerequisites. |