Sean

Inference with ONNXRuntime

2

- refactor pytorch2onnx: - load hyperparameters from the specific configure file - use dynamic axes instead of fixed axes to support actual usage - add inference API with onnxruntime

cache prompt variables

1

The prompt variables are obtained in real-time when calling the `fit` function in the previous implementation. It might be inefficient because the `fit()` tends to be called multiple times in...

https://github.com/Textualize/rich

- fix bug: attention_mask=None - upgrade transformers