@@ -296,18 +296,49 @@ The predicted tokens will then be placed between the sentinel tokens.
If you'd like a faster training and inference performance, install [apex](https://github.com/NVIDIA/apex#quick-start) and then the model will automatically use `apex.normalization.FusedRMSNorm` instead of `T5LayerNorm`. The former uses an optimized fused kernel which is several times faster than the latter.
## Example scripts
## Resources
T5 is supported by several example scripts, both for pre-training and fine-tuning.
A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with T5. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
- pre-training: the [run_t5_mlm_flax.py](https://github.com/huggingface/transformers/blob/main/examples/flax/language-modeling/run_t5_mlm_flax.py)
script allows you to further pre-train T5 or pre-train T5 from scratch on your own data. The [t5_tokenizer_model.py](https://github.com/huggingface/transformers/blob/main/examples/flax/language-modeling/t5_tokenizer_model.py)
script allows you to further train a T5 tokenizer or train a T5 Tokenizer from scratch on your own data. Note that
Flax (a neural network library on top of JAX) is particularly useful to train on TPU hardware.
<PipelineTag pipeline="text-classification"/>
- fine-tuning: T5 is supported by the official summarization scripts ([PyTorch](https://github.com/huggingface/transformers/tree/main/examples/pytorch/summarization), [Tensorflow](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/summarization), and [Flax](https://github.com/huggingface/transformers/tree/main/examples/flax/summarization)) and translation scripts
([PyTorch](https://github.com/huggingface/transformers/tree/main/examples/pytorch/translation) and [Tensorflow](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/translation)). These scripts allow
you to easily fine-tune T5 on custom data for summarization/translation.
- A notebook for how to [finetune T5 for classification and multiple choice](https://colab.research.google.com/github/patil-suraj/exploring-T5/blob/master/t5_fine_tuning.ipynb).
- A notebook for how to [finetune T5 for sentiment span extraction](https://colab.research.google.com/github/enzoampil/t5-intro/blob/master/t5_qa_training_pytorch_span_extraction.ipynb). 🌎
<PipelineTag pipeline="token-classification"/>
- A notebook for how to [finetune T5 for named entity recognition](https://colab.research.google.com/drive/1obr78FY_cBmWY5ODViCmzdY6O1KB65Vc?usp=sharing). 🌎
<PipelineTag pipeline="text-generation"/>
- A notebook for [Finetuning CodeT5 for generating docstrings from Ruby code](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/T5/Fine_tune_CodeT5_for_generating_docstrings_from_Ruby_code.ipynb).
<PipelineTag pipeline="summarization"/>
- A notebook to [Finetune T5-base-dutch to perform Dutch abstractive summarization on a TPU](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/T5/Fine_tuning_Dutch_T5_base_on_CNN_Daily_Mail_for_summarization_(on_TPU_using_HuggingFace_Accelerate).ipynb).
- A notebook for how to [finetune T5 for summarization in PyTorch and track experiments with WandB](https://colab.research.google.com/github/abhimishra91/transformers-tutorials/blob/master/transformers_summarization_wandb.ipynb#scrollTo=OKRpFvYhBauC). 🌎
- A blog post on [Distributed Training: Train BART/T5 for Summarization using 🤗 Transformers and Amazon SageMaker](https://huggingface.co/blog/sagemaker-distributed-training-seq2seq).
- [`T5ForConditionalGeneration`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/summarization) and [noteboook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/summarization.ipynb).
- [`TFT5ForConditionalGeneration`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/summarization) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/summarization-tf.ipynb).
- [`FlaxT5ForConditionalGeneration`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/flax/summarization).
- [Summarization](https://huggingface.co/course/chapter7/5?fw=pt#summarization) chapter of the 🤗 Hugging Face course.
<PipelineTag pipeline="fill-mask"/>
- [`FlaxT5ForConditionalGeneration`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/flax/language-modeling#t5-like-span-masked-language-modeling) for training T5 with a span-masked language model objective. The script also shows how to train a T5 tokenizer. [`FlaxT5ForConditionalGeneration`] is also supported by this [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/masked_language_modeling_flax.ipynb).
<PipelineTag pipeline="translation"/>
- [`T5ForConditionalGeneration`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/translation) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/translation.ipynb).
- [`TFT5ForConditionalGeneration`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/translation) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/translation-tf.ipynb).
<PipelineTag pipeline="question-answering"/>
- A notebook on how to [finetune T5 for question answering with TensorFlow 2](https://colab.research.google.com/github/snapthat/TF-T5-text-to-text/blob/master/snapthatT5/notebooks/TF-T5-Datasets%20Training.ipynb). 🌎
- A notebook on how to [finetune T5 for question answering on a TPU](https://colab.research.google.com/github/patil-suraj/exploring-T5/blob/master/T5_on_TPU.ipynb#scrollTo=QLGiFCDqvuil).
🚀 **Deploy**
- A blog post on how to deploy [T5 11B for inference for less than $500](https://www.philschmid.de/deploy-t5-11b).
