Resources

For Q&A fine-tune training

From HF course

Course:

https://huggingface.co/learn/nlp-course/en/chapter7/7

In Colab:

https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/question_answering.ipynb

Under-the-hood:

https://github.com/huggingface/transformers/blob/v4.44.2/src/transformers/models/bert/modeling_bert.py#L1930

Pytorch

Manual code with PyTorch, from HF:

https://github.com/huggingface/transformers/blob/main/examples/pytorch/question-answering/run_qa.py
https://github.com/huggingface/transformers/blob/main/examples/pytorch/question-answering/trainer_qa.py

Tensorflow

Official Google BERT squad training:

https://github.com/google-research/bert/blob/master/run_squad.py

Colab:

https://colab.research.google.com/github/tensorflow/tpu/blob/master/tools/colab/bert_finetuning_with_cloud_tpus.ipynb

Other

https://github.com/kushalj001/pytorch-question-answering

https://github.com/NVIDIA/DeepLearningExamples/blob/master/PaddlePaddle/LanguageModeling/BERT/modeling.py#L238