0616039115
* Implemented a new version of Kernel and the CustomOp to support output that matches the HuggingFace model's input without the need for intermediate python logic. * Implemented a e2e tutorial for exporting and inferencing using the HuggingFace's QuestionAnsering model. Known Issue: Python side doesn't have an implementation of Bert Decoder and so the augmented model is only half-complete. At the time of inferencing the HuggingFace tokenizer is used to decode the result back to string. |
||
---|---|---|
.. | ||
data/gpt-2 | ||
bert_e2e.py | ||
cpp_custom_ops_tutorial.md | ||
gpt2bs.py | ||
hf_bert_e2e.py | ||
imagenet_processing.ipynb | ||
pytorch_custom_ops_tutorial.ipynb | ||
tf2onnx_custom_ops_tutorial.ipynb |