shairoz-deci

ValueError: Operands could not be broadcast together with shapes , when converting with change_ordering

1

**Describe the bug** When loading a model and trying to convert it from pytorch to keras with change_ordering=True, I get an error. is there a way to resolve or figure...

Thank you for sharing this repo. I've tried training TinyBert - 4L on squad V2. The steps I took are as follows: 1. I've downloaded the pre-trained wikipedia checkpoint 2....

TinyBert fine tune SQuAD

2

Thank you for sharing this great repo. Can you please provide instructions, or code if available, for task distillation on the SQuAD dataset? Thanks in advance

Wikipedia with proper data format

1

Thank you for releasing and maintaining this repo. Can you please provide a link to the wikipedia dataset, and additional datasets required to train TinyBert from scratch, in the required...

Including task loss

1

Thank you for sharing this repo. I have a question about the loss used to train TinyBert. Unlike DistilBert, MobileBert and other distillation based BERT variants, TinyBert training doesn't include...

Trying to build CenterNet on pytorch1.6, fail to build DCN

4

I am trying to run CenterNet on pytorch 1.6, I followed the steps on https://github.com/xingyizhou/CenterNet/issues/7 and I'm failing on the second stage, building the DCNv2 from the original repo. `python...

Thank you for sharing your findings. Regarding the Huggingface infinity comparison under https://github.com/powderluv/transformer-benchmarks/tree/main/hf.co_1ms just to verify, which machine did you run you CPU experiment? did you use a single core,...

error trying to train squad /tokenizer/roberta.so: undefined symbol: _Py_ZeroStruct

1

Thank you for sharing the code for fine-tuning Roberta. I've been trying to train Roberta-base on squad v2 and I am getting the following error with this command: ``` python...