Notebooks with examples
🌍 Transformers Notebooks
You can find here a list of the official notebooks provided by BOINC AI.
Also, we would like to list here interesting content created by the community. If you wrote some notebook(s) leveraging 🌍 Transformers and would like to be listed here, please open a Pull Request so it can be included under the Community notebooks.
BOINC AI’s notebooks 🌍
Documentation notebooks
You can open any page of the documentation as a notebook in Colab (there is a button directly on said pages) but they are also listed here if you need them:
PyTorch Examples
Natural Language Processing
Show how to preprocess the data and fine-tune a pretrained model on any GLUE task.
Show how to preprocess the data and fine-tune a pretrained model on a causal or masked LM task.
Show how to preprocess the data and fine-tune a pretrained model on a token classification task (NER, PoS).
Show how to preprocess the data and fine-tune a pretrained model on SQUAD.
Show how to preprocess the data and fine-tune a pretrained model on SWAG.
Show how to preprocess the data and fine-tune a pretrained model on WMT.
Show how to preprocess the data and fine-tune a pretrained model on XSUM.
Highlight all the steps to effectively train Transformer model on custom data
How to guide language generation with user-provided constraints
Computer Vision
Show how to preprocess the data using Torchvision and fine-tune any pretrained Vision model on Image Classification
Show how to preprocess the data using Albumentations and fine-tune any pretrained Vision model on Image Classification
Show how to preprocess the data using Kornia and fine-tune any pretrained Vision model on Image Classification
Show how to perform zero-shot object detection on images with text queries
Show how to fine-tune BLIP for image captioning on a custom dataset
Show how to build an image similarity system
Show how to preprocess the data and fine-tune a pretrained SegFormer model on Semantic Segmentation
Show how to preprocess the data and fine-tune a pretrained VideoMAE model on Video Classification
Audio
Show how to preprocess the data and fine-tune a pretrained Speech model on TIMIT
Show how to preprocess the data and fine-tune a multi-lingually pretrained speech model on Common Voice
Show how to preprocess the data and fine-tune a pretrained Speech model on Keyword Spotting
Biological Sequences
See how to tokenize proteins and fine-tune a large pre-trained protein “language” model
See how to go from protein sequence to a full protein model and PDB file
See how to tokenize DNA and fine-tune a large pre-trained DNA “language” model
Train even larger DNA models in a memory-efficient way
Other modalities
Utility notebooks
TensorFlow Examples
Natural Language Processing
Show how to preprocess the data and fine-tune a pretrained model on any GLUE task.
Show how to preprocess the data and fine-tune a pretrained model on a causal or masked LM task.
Show how to preprocess the data and fine-tune a pretrained model on a token classification task (NER, PoS).
Show how to preprocess the data and fine-tune a pretrained model on SQUAD.
Show how to preprocess the data and fine-tune a pretrained model on SWAG.
Show how to preprocess the data and fine-tune a pretrained model on WMT.
Show how to preprocess the data and fine-tune a pretrained model on XSUM.
Computer Vision
Show how to preprocess the data and fine-tune any pretrained Vision model on Image Classification
Show how to preprocess the data and fine-tune a pretrained SegFormer model on Semantic Segmentation
Biological Sequences
See how to tokenize proteins and fine-tune a large pre-trained protein “language” model
Utility notebooks
Optimum notebooks
🌍 Optimum is an extension of 🌍 Transformers, providing a set of performance optimization tools enabling maximum efficiency to train and run models on targeted hardwares.
Show how to apply static, dynamic and aware training quantization on a model using Intel Neural Compressor (INC) for any GLUE task.
Community notebooks:
More notebooks developed by the community are available here.
Last updated
