Vikas Kumar Ojha

If you clone the repository and install the fastwer using setup.py file. By command python setup.py install. The module has no attribute problem will be resolved. Also make sure you...

You can generate in this way: gen_tok=["generate question: [hl] Python [hl] is an interpreted, high-level, general-purpose programming language. Created by Guido van Rossum and first released in 1991, Python's design...

Read this blog: https://medium.com/geekculture/converting-yolo-v7-to-tensorflow-lite-for-mobile-deployment-ebc1103e8d1e

Please check this blog it converts the YOLO v7 to tensorflow lite. https://medium.com/geekculture/converting-yolo-v7-to-tensorflow-lite-for-mobile-deployment-ebc1103e8d1e

Yes happened with me as well. Its internal issue of TensorRT. I even tried with the latest 8.4 release as well. For 512 tokens the model was more than 2x...

@pommedeterresautee You mean in TensorRT repo they export the model without past key values hence that's the reason right?.

@pommedeterresautee Thanks for sharing sir.

@Jumabek Doesn't TF support both channel first and channel last format?. The same model can be used as it is in TF. The user will just have to swap the...

@lakshaykc Is model performing worse on larger sequences?

I have created the quantization support in a separate fork of this repo which can be checked here https://github.com/VikasOjha666/parseq By default when the model is trained it will be trained...