Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/manuelyhvh/nlp-with-transformers
https://github.com/manuelyhvh/nlp-with-transformers
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/manuelyhvh/nlp-with-transformers
- Owner: manuelyhvh
- License: apache-2.0
- Created: 2022-02-02T23:24:27.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2022-02-02T23:24:50.000Z (almost 3 years ago)
- Last Synced: 2024-05-27T11:49:04.250Z (6 months ago)
- Language: Jupyter Notebook
- Size: 12.5 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-studio-lab-jp - Natural Language Processing with Transformers
README
# Transformers Notebooks
This repository contains the example code from our O'Reilly book [Natural Language Processing with Transformers](https://learning.oreilly.com/library/view/natural-language-processing/9781098103231/):
## Getting started
You can run these notebooks on cloud platforms like [Google Colab](https://colab.research.google.com/) or your local machine. Note that most chapters require a GPU to run in a reasonable amount of time, so we recommend one of the cloud platforms as they come pre-installed with CUDA.
### Running on a cloud platform
To run these notebooks on a cloud platform, just click on one of the badges in the table below:
| Chapter | Colab | Kaggle | Gradient | Studio Lab |
|:--------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Introduction | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/01_introduction.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/01_introduction.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/01_introduction.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/01_introduction.ipynb) |
| Text Classification | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/02_classification.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/02_classification.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/02_classification.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/02_classification.ipynb) |
| Transformer Anatomy | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/03_transformer-anatomy.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/03_transformer-anatomy.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/03_transformer-anatomy.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/03_transformer-anatomy.ipynb) |
| Multilingual Named Entity Recognition | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/04_multilingual-ner.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/04_multilingual-ner.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/04_multilingual-ner.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/04_multilingual-ner.ipynb) |
| Text Generation | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/05_text-generation.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/05_text-generation.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/05_text-generation.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/05_text-generation.ipynb) |
| Summarization | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/06_summarization.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/06_summarization.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/06_summarization.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/06_summarization.ipynb) |
| Question Answering | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/07_question-answering.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/07_question-answering.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/07_question-answering.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/07_question-answering.ipynb) |
| Making Transformers Efficient in Production | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/08_model-compression.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/08_model-compression.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/08_model-compression.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/08_model-compression.ipynb) |
| Dealing with Few to No Labels | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/09_few-to-no-labels.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/09_few-to-no-labels.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/09_few-to-no-labels.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/09_few-to-no-labels.ipynb) |
| Training Transformers from Scratch | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/10_transformers-from-scratch.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/10_transformers-from-scratch.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/10_transformers-from-scratch.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/10_transformers-from-scratch.ipynb) |
| Future Directions | [](https://colab.research.google.com/github/nlp-with-transformers/notebooks/blob/main/11_future-directions.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/nlp-with-transformers/notebooks/blob/main/11_future-directions.ipynb) | [](https://console.paperspace.com/github/nlp-with-transformers/notebooks/blob/main/11_future-directions.ipynb) | [](https://studiolab.sagemaker.aws/import/github/nlp-with-transformers/notebooks/blob/main/11_future-directions.ipynb) |
Nowadays, the GPUs on Colab tend to be K80s (which have limited memory), so we recommend using [Kaggle](https://www.kaggle.com/docs/notebooks), [Gradient](https://gradient.run/notebooks), or [SageMaker Studio Lab]((https://studiolab.sagemaker.aws/)). These platforms tend to provide more performant GPUs like P100s, all for free!
### Running on your machine
To run the notebooks on your own machine, first clone the repository:
```
git clone https://github.com/nlp-with-transformers/notebooks
cd notebooks-test
```
Next, you'll need to install a few packages that depend on your operating system and hardware:
* [PyTorch](https://pytorch.org/get-started/locally/)
* [TensorFlow](https://www.tensorflow.org/install/) (optional, since only used in a few chapters)
* [PyTorch Scatter](https://github.com/rusty1s/pytorch_scatter) (only used in Chapter 11)
* [librosa](https://librosa.org/) (only used in Chapter 11)
* [libsndfile](http://www.mega-nerd.com/libsndfile/) (only used in Chapter 11)
Once you have install the above requirements, create a virtual environment and install the remaining Python dependencies:
```
conda create -n book python=3.8 -y && conda activate book
from install import *
install_requirements()
# Use the following to run Chapter 7
# install_requirements(is_chapter7)
```