State-of-the-art Natural Language Processing (NLP) for TensorFlow 2.0 and PyTorch.
🤗 Transformers (formerly known as `pytorch-transformers` and `pytorch-pretrained-bert`) provides general-purpose architectures (BERT, GPT, GPT-2, RoBERTa, XLM, DistilBert, XLNet...) for Natural Language Understanding (NLU) and Natural Language Generation (NLG) with more than 32+ pretrained checkpoints in 100+ languages.
Features
- As easy to use as pytorch-transformers
- As powerful and concise as Keras
- High performance on NLU and NLG tasks
- Low barrier to entry for educators and practitioners
State-of-the-art NLP for everyone
- Deep learning researchers
- Hands-on practitioners
- AI/ML/NLP teachers and educators
Lower compute costs, smaller carbon footprint
- Researchers can share trained models instead of always retraining
- Practitioners can reduce compute time and production costs
- 8 architectures with over 30 pretrained models, some in more than 100 languages
Choose the right framework for every part of a model's lifetime
- Train state-of-the-art models in 3 lines of code
- Deep interoperability between TensorFlow 2.0 and PyTorch models
- Move a single model between TF2.0/PyTorch frameworks at will
- Seamlessly pick the right framework for training, evaluation, production
PyTorch-Transformers (formerly known as `pytorch-pretrained-bert`) is a library of state-of-the-art pre-trained models for Natural Language Processing (NLP).
The library currently contains PyTorch implementations, pre-trained model weights, usage scripts and conversion utilities for the following models:
1.**[BERT](https://github.com/google-research/bert)** (from Google) released with the paper [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805) by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova.
2.**[GPT](https://github.com/openai/finetune-transformer-lm)** (from OpenAI) released with the paper [Improving Language Understanding by Generative Pre-Training](https://blog.openai.com/language-unsupervised/) by Alec Radford, Karthik Narasimhan, Tim Salimans and Ilya Sutskever.
3.**[GPT-2](https://blog.openai.com/better-language-models/)** (from OpenAI) released with the paper [Language Models are Unsupervised Multitask Learners](https://blog.openai.com/better-language-models/) by Alec Radford*, Jeffrey Wu*, Rewon Child, David Luan, Dario Amodei** and Ilya Sutskever**.
4.**[Transformer-XL](https://github.com/kimiyoung/transformer-xl)** (from Google/CMU) released with the paper [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://arxiv.org/abs/1901.02860) by Zihang Dai*, Zhilin Yang*, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov.
5.**[XLNet](https://github.com/zihangdai/xlnet/)** (from Google/CMU) released with the paper [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://arxiv.org/abs/1906.08237) by Zhilin Yang*, Zihang Dai*, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le.
6.**[XLM](https://github.com/facebookresearch/XLM/)** (from Facebook) released together with the paper [Cross-lingual Language Model Pretraining](https://arxiv.org/abs/1901.07291) by Guillaume Lample and Alexis Conneau.
7.**[RoBERTa](https://github.com/pytorch/fairseq/tree/master/examples/roberta)** (from Facebook), released together with the paper a [Robustly Optimized BERT Pretraining Approach](https://arxiv.org/abs/1907.11692) by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov.
8.**[DistilBERT](https://github.com/huggingface/pytorch-transformers/tree/master/examples/distillation)** (from HuggingFace), released together with the blogpost [Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT](https://medium.com/huggingface/distilbert-8cf3380435b5
) by Victor Sanh, Lysandre Debut and Thomas Wolf.
These implementations have been tested on several datasets (see the example scripts) and should match the performances of the original implementations (e.g. ~93 F1 on SQuAD for BERT Whole-Word-Masking, ~88 F1 on RocStories for OpenAI GPT, ~18.3 perplexity on WikiText 103 for Transformer-XL, ~0.916 Peason R coefficient on STS-B for XLNet). You can find more details on the performances in the Examples section of the [documentation](https://huggingface.co/pytorch-transformers/examples.html).
| Section | Description |
|-|-|
| [Installation](#installation) | How to install the package |
| [Quick tour: TF 2.0 and PyTorch ](#Quick-tour-TF-2.0-training-and-PyTorch-interoperability) | Train a TF 2.0 model in 10 lines of code, load it in PyTorch |
| [Quick tour: Fine-tuning/usage scripts](#quick-tour-of-the-fine-tuningusage-scripts) | Using provided scripts: GLUE, SQuAD and Text generation |
| [Migrating from pytorch-pretrained-bert to pytorch-transformers](#Migrating-from-pytorch-pretrained-bert-to-pytorch-transformers) | Migrating your code from pytorch-pretrained-bert to pytorch-transformers |
| [Documentation](https://huggingface.co/pytorch-transformers/) | Full API documentation and more |
| [Migrating from pytorch-transformers to transformers](#Migrating-from-pytorch-pretrained-bert-to-transformers) | Migrating your code from pytorch-pretrained-bert to transformers |
| [Migrating from pytorch-pretrained-bert to pytorch-transformers](#Migrating-from-pytorch-pretrained-bert-to-transformers) | Migrating your code from pytorch-pretrained-bert to transformers |
| [Documentation](https://huggingface.co/transformers/) | Full API documentation and more |
## Installation
...
...
@@ -33,10 +63,10 @@ This repo is tested on Python 2.7 and 3.5+ (examples are tested only on python 3
### With pip
PyTorch-Transformers can be installed by pip as follows:
Transformers can be installed by pip as follows:
```bash
pip install pytorch-transformers
pip install transformers
```
### From source
...
...
@@ -49,14 +79,14 @@ pip install [--editable] .
### Tests
A series of tests is included for the library and the example scripts. Library tests can be found in the [tests folder](https://github.com/huggingface/pytorch-transformers/tree/master/pytorch_transformers/tests) and examples tests in the [examples folder](https://github.com/huggingface/pytorch-transformers/tree/master/examples).
A series of tests is included for the library and the example scripts. Library tests can be found in the [tests folder](https://github.com/huggingface/transformers/tree/master/transformers/tests) and examples tests in the [examples folder](https://github.com/huggingface/transformers/tree/master/examples).
These tests can be run using `pytest` (install pytest if needed with `pip install pytest`).
You can run the tests from the root of the cloned repository with the commands:
@@ -69,6 +99,22 @@ It contains an example of a conversion script from a Pytorch trained Transformer
At some point in the future, you'll be able to seamlessly move from pre-training or fine-tuning models in PyTorch to productizing them in CoreML,
or prototype a model or an app in CoreML then research its hyperparameters or architecture from PyTorch. Super exciting!
## Model architectures
🤗 Transformers currently provides 8 NLU/NLG architectures:
1.**[BERT](https://github.com/google-research/bert)** (from Google) released with the paper [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805) by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova.
2.**[GPT](https://github.com/openai/finetune-transformer-lm)** (from OpenAI) released with the paper [Improving Language Understanding by Generative Pre-Training](https://blog.openai.com/language-unsupervised/) by Alec Radford, Karthik Narasimhan, Tim Salimans and Ilya Sutskever.
3.**[GPT-2](https://blog.openai.com/better-language-models/)** (from OpenAI) released with the paper [Language Models are Unsupervised Multitask Learners](https://blog.openai.com/better-language-models/) by Alec Radford*, Jeffrey Wu*, Rewon Child, David Luan, Dario Amodei** and Ilya Sutskever**.
4.**[Transformer-XL](https://github.com/kimiyoung/transformer-xl)** (from Google/CMU) released with the paper [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://arxiv.org/abs/1901.02860) by Zihang Dai*, Zhilin Yang*, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov.
5.**[XLNet](https://github.com/zihangdai/xlnet/)** (from Google/CMU) released with the paper [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://arxiv.org/abs/1906.08237) by Zhilin Yang*, Zihang Dai*, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le.
6.**[XLM](https://github.com/facebookresearch/XLM/)** (from Facebook) released together with the paper [Cross-lingual Language Model Pretraining](https://arxiv.org/abs/1901.07291) by Guillaume Lample and Alexis Conneau.
7.**[RoBERTa](https://github.com/pytorch/fairseq/tree/master/examples/roberta)** (from Facebook), released together with the paper a [Robustly Optimized BERT Pretraining Approach](https://arxiv.org/abs/1907.11692) by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov.
8.**[DistilBERT](https://github.com/huggingface/transformers/tree/master/examples/distillation)** (from HuggingFace), released together with the blogpost [Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT](https://medium.com/huggingface/distilbert-8cf3380435b5
) by Victor Sanh, Lysandre Debut and Thomas Wolf.
These implementations have been tested on several datasets (see the example scripts) and should match the performances of the original implementations (e.g. ~93 F1 on SQuAD for BERT Whole-Word-Masking, ~88 F1 on RocStories for OpenAI GPT, ~18.3 perplexity on WikiText 103 for Transformer-XL, ~0.916 Peason R coefficient on STS-B for XLNet). You can find more details on the performances in the Examples section of the [documentation](https://huggingface.co/transformers/examples.html).
## Online demo
**[Write With Transformer](https://transformer.huggingface.co)**, built by the Hugging Face team at transformer.huggingface.co, is the official demo of this repo’s text generation capabilities.
...
...
@@ -80,22 +126,25 @@ You can use it to experiment with completions generated by `GPT2Model`, `Transfo
## Quick tour
Let's do a very quick overview of PyTorch-Transformers. Detailed examples for each model architecture (Bert, GPT, GPT-2, Transformer-XL, XLNet and XLM) can be found in the [full documentation](https://huggingface.co/pytorch-transformers/).
Let's do a very quick overview of the model architectures in 🤗 Transformers. Detailed examples for each model architecture (Bert, GPT, GPT-2, Transformer-XL, XLNet and XLM) can be found in the [full documentation](https://huggingface.co/transformers/).
```python
importtorch
frompytorch_transformersimport*
fromtransformersimport*
# PyTorch-Transformers has a unified API
# for 7 transformer architectures and 30 pretrained weights.
# Transformers has a unified API
# for 8 transformer architectures and 30 pretrained weights.
# To use TensorFlow 2.0 versions of the models, simply prefix the class names with 'TF', e.g. `TFRobertaModel` is the TF 2.0 counterpart of the PyTorch model `RobertaModel`
# Let's encode some text in a sequence of hidden-states using each model:
# SOTA examples for GLUE, SQUAD, text generation...
```
## Quick tour TF 2.0 training and PyTorch interoperability
Let's do a quick example of how a TensorFlow 2.0 model can be trained in 12 lines of code with 🤗 Transformers and then loaded in PyTorch for fast inspection/tests.
```python
importtensorflowastf
importtensorflow_datasets
frompytorch_transformersimport*
# Load dataset, tokenizer, model from pretrained model/vocabulary
## Migrating from pytorch-pretrained-bert to pytorch-transformers
## Migrating from pytorch-transformers to transformers
Here is a quick summary of what you should take care of when migrating from `pytorch-transformers` to `transformers`.
### Positional order of some models' keywords inputs (`attention_mask`, `token_type_ids`...) changed
To be able to use Torchscript (see #1010, #1204 and #1195) the specific order of some models **keywords inputs** (`attention_mask`, `token_type_ids`...) has been changed.
If you used to call the models with keyword names for keyword arguments, e.g. `model(inputs_ids, attention_mask=attention_mask, token_type_ids=token_type_ids)`, this should not cause any change.
If you used to call the models with positional inputs for keyword arguments, e.g. `model(inputs_ids, attention_mask, token_type_ids)`, you may have to double check the exact order of input arguments.
## Migrating from pytorch-pretrained-bert to transformers
Here is a quick summary of what you should take care of when migrating from `pytorch-pretrained-bert` to `pytorch-transformers`
Here is a quick summary of what you should take care of when migrating from `pytorch-pretrained-bert` to `transformers`.
### Models always output `tuples`
The main breaking change when migrating from `pytorch-pretrained-bert` to `pytorch-transformers` is that the models forward method always outputs a `tuple` with various elements depending on the model and the configuration parameters.
The main breaking change when migrating from `pytorch-pretrained-bert` to `transformers` is that the models forward method always outputs a `tuple` with various elements depending on the model and the configuration parameters.
The exact content of the tuples for each model are detailed in the models' docstrings and the [documentation](https://huggingface.co/pytorch-transformers/).
The exact content of the tuples for each model are detailed in the models' docstrings and the [documentation](https://huggingface.co/transformers/).
In pretty much every case, you will be fine by taking the first element of the output as the output you previously used in `pytorch-pretrained-bert`.
Here is a `pytorch-pretrained-bert` to `pytorch-transformers` conversion example for a `BertForSequenceClassification` classification model:
Here is a `pytorch-pretrained-bert` to `transformers` conversion example for a `BertForSequenceClassification` classification model:
```python
# Let's load our model
...
...
@@ -320,11 +429,11 @@ model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
# If you used to have this line in pytorch-pretrained-bert:
loss=model(input_ids,labels=labels)
# Now just use this line in pytorch-transformers to extract the loss from the output tuple:
# Now just use this line in transformers to extract the loss from the output tuple:
outputs=model(input_ids,labels=labels)
loss=outputs[0]
# In pytorch-transformers you can also have access to the logits:
# In transformers you can also have access to the logits:
loss,logits=outputs[:2]
# And even the attention weights if you configure the model to output them (and other outputs too, see the docstrings and documentation)
...
...
@@ -339,7 +448,7 @@ Breaking change in the `from_pretrained()`method:
1. Models are now set in evaluation mode by default when instantiated with the `from_pretrained()` method. To train them don't forget to set them back in training mode (`model.train()`) to activate the dropout modules.
2. The additional `*input` and `**kwargs` arguments supplied to the `from_pretrained()` method used to be directly passed to the underlying model's class `__init__()` method. They are now used to update the model configuration attribute instead which can break derived model classes build based on the previous `BertForSequenceClassification` examples. We are working on a way to mitigate this breaking change in [#866](https://github.com/huggingface/pytorch-transformers/pull/866) by forwarding the the model `__init__()` method (i) the provided positional arguments and (ii) the keyword arguments which do not match any configuration class attributes.
2. The additional `*input` and `**kwargs` arguments supplied to the `from_pretrained()` method used to be directly passed to the underlying model's class `__init__()` method. They are now used to update the model configuration attribute instead which can break derived model classes build based on the previous `BertForSequenceClassification` examples. We are working on a way to mitigate this breaking change in [#866](https://github.com/huggingface/transformers/pull/866) by forwarding the the model `__init__()` method (i) the provided positional arguments and (ii) the keyword arguments which do not match any configuration class attributes.
Also, while not a breaking change, the serialization methods have been standardized and you probably should switch to the new method `save_pretrained(save_directory)` if you were using any other serialization method before.
...
...
@@ -396,7 +505,7 @@ for batch in train_data:
loss.backward()
optimizer.step()
### In PyTorch-Transformers, optimizer and schedules are splitted and instantiated like this:
### In Transformers, optimizer and schedules are splitted and instantiated like this:
optimizer=AdamW(model.parameters(),lr=lr,correct_bias=False)# To reproduce BertAdam specific behavior set correct_bias=False
At the moment, there is no paper associated to PyTorch-Transformers but we are working on preparing one. In the meantime, please include a mention of the library and a link to the present repository if you use this work in a published or open-source project.
At the moment, there is no paper associated to Transformers but we are working on preparing one. In the meantime, please include a mention of the library and a link to the present repository if you use this work in a published or open-source project.
@@ -15,4 +15,4 @@ In order to help this new field develop, we have included a few additional featu
* accessing all the attention weights for each head of BERT/GPT/GPT-2,
* retrieving heads output values and gradients to be able to compute head importance score and prune head as explained in https://arxiv.org/abs/1905.10650.
To help you understand and use these features, we have added a specific example script: `bertology.py <https://github.com/huggingface/pytorch-transformers/blob/master/examples/run_bertology.py>`_ while extract information and prune a model pre-trained on GLUE.
To help you understand and use these features, we have added a specific example script: `bertology.py <https://github.com/huggingface/transformers/blob/master/examples/run_bertology.py>`_ while extract information and prune a model pre-trained on GLUE.
@@ -6,7 +6,7 @@ A command-line interface is provided to convert original Bert/GPT/GPT-2/Transfor
BERT
^^^^
You can convert any TensorFlow checkpoint for BERT (in particular `the pre-trained models released by Google <https://github.com/google-research/bert#pre-trained-models>`_\ ) in a PyTorch save file by using the `convert_tf_checkpoint_to_pytorch.py <https://github.com/huggingface/pytorch-transformers/blob/master/pytorch_transformers/convert_tf_checkpoint_to_pytorch.py>`_ script.
You can convert any TensorFlow checkpoint for BERT (in particular `the pre-trained models released by Google <https://github.com/google-research/bert#pre-trained-models>`_\ ) in a PyTorch save file by using the `convert_tf_checkpoint_to_pytorch.py <https://github.com/huggingface/transformers/blob/master/transformers/convert_tf_checkpoint_to_pytorch.py>`_ script.
This CLI takes as input a TensorFlow checkpoint (three files starting with ``bert_model.ckpt``\ ) and the associated configuration file (\ ``bert_config.json``\ ), and creates a PyTorch model for this configuration, loads the weights from the TensorFlow checkpoint in the PyTorch model and saves the resulting model in a standard PyTorch save file that can be imported using ``torch.load()`` (see examples in `run_bert_extract_features.py <https://github.com/huggingface/pytorch-pretrained-BERT/tree/master/examples/run_bert_extract_features.py>`_\ , `run_bert_classifier.py <https://github.com/huggingface/pytorch-pretrained-BERT/tree/master/examples/run_bert_classifier.py>`_ and `run_bert_squad.py <https://github.com/huggingface/pytorch-pretrained-BERT/tree/master/examples/run_bert_squad.py>`_\ ).
...
...
@@ -20,7 +20,7 @@ Here is an example of the conversion process for a pre-trained ``BERT-Base Uncas
PyTorch-Transformers is a library of state-of-the-art pre-trained models for Natural Language Processing (NLP).
Transformers is a library of state-of-the-art pre-trained models for Natural Language Processing (NLP).
The library currently contains PyTorch implementations, pre-trained model weights, usage scripts and conversion utilities for the following models:
...
...
@@ -12,7 +12,7 @@ The library currently contains PyTorch implementations, pre-trained model weight
5. `XLNet <https://github.com/zihangdai/xlnet>`_ (from Google/CMU) released with the paper `XLNet: Generalized Autoregressive Pretraining for Language Understanding <https://arxiv.org/abs/1906.08237>`_ by Zhilin Yang*, Zihang Dai*, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le.
6. `XLM <https://github.com/facebookresearch/XLM>`_ (from Facebook) released together with the paper `Cross-lingual Language Model Pretraining <https://arxiv.org/abs/1901.07291>`_ by Guillaume Lample and Alexis Conneau.
7. `RoBERTa <https://github.com/pytorch/fairseq/tree/master/examples/roberta>`_ (from Facebook), released together with the paper a `Robustly Optimized BERT Pretraining Approach <https://arxiv.org/abs/1907.11692>`_ by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov.
8. `DistilBERT <https://huggingface.co/pytorch-transformers/model_doc/distilbert.html>`_ (from HuggingFace) released together with the blog post `Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT <https://medium.com/huggingface/distilbert-8cf3380435b5>`_ by Victor Sanh, Lysandre Debut and Thomas Wolf.
8. `DistilBERT <https://huggingface.co/transformers/model_doc/distilbert.html>`_ (from HuggingFace) released together with the blog post `Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT <https://medium.com/huggingface/distilbert-8cf3380435b5>`_ by Victor Sanh, Lysandre Debut and Thomas Wolf.
An extensive test suite is included to test the library behavior and several examples. Library tests can be found in the `tests folder <https://github.com/huggingface/pytorch-transformers/tree/master/pytorch_transformers/tests>`_ and examples tests in the `examples folder <https://github.com/huggingface/pytorch-transformers/tree/master/examples>`_.
An extensive test suite is included to test the library behavior and several examples. Library tests can be found in the `tests folder <https://github.com/huggingface/transformers/tree/master/transformers/tests>`_ and examples tests in the `examples folder <https://github.com/huggingface/transformers/tree/master/examples>`_.
Tests can be run using `pytest` (install pytest if needed with `pip install pytest`).
...
...
@@ -35,7 +35,7 @@ Run all the tests from the root of the cloned repository with the commands:
Here is a quick summary of what you should take care of when migrating from `pytorch-pretrained-bert` to `pytorch-transformers`
Here is a quick summary of what you should take care of when migrating from `pytorch-pretrained-bert` to `transformers`
### Models always output `tuples`
The main breaking change when migrating from `pytorch-pretrained-bert` to `pytorch-transformers` is that the models forward method always outputs a `tuple` with various elements depending on the model and the configuration parameters.
The main breaking change when migrating from `pytorch-pretrained-bert` to `transformers` is that the models forward method always outputs a `tuple` with various elements depending on the model and the configuration parameters.
The exact content of the tuples for each model are detailled in the models' docstrings and the [documentation](https://huggingface.co/pytorch-transformers/).
The exact content of the tuples for each model are detailled in the models' docstrings and the [documentation](https://huggingface.co/transformers/).
In pretty much every case, you will be fine by taking the first element of the output as the output you previously used in `pytorch-pretrained-bert`.
Here is a `pytorch-pretrained-bert` to `pytorch-transformers` conversion example for a `BertForSequenceClassification` classification model:
Here is a `pytorch-pretrained-bert` to `transformers` conversion example for a `BertForSequenceClassification` classification model:
```python
# Let's load our model
...
...
@@ -20,11 +20,11 @@ model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
# If you used to have this line in pytorch-pretrained-bert:
loss=model(input_ids,labels=labels)
# Now just use this line in pytorch-transformers to extract the loss from the output tuple:
# Now just use this line in transformers to extract the loss from the output tuple:
outputs=model(input_ids,labels=labels)
loss=outputs[0]
# In pytorch-transformers you can also have access to the logits:
# In transformers you can also have access to the logits:
loss,logits=outputs[:2]
# And even the attention weigths if you configure the model to output them (and other outputs too, see the docstrings and documentation)
...
...
@@ -96,7 +96,7 @@ for batch in train_data:
loss.backward()
optimizer.step()
### In PyTorch-Transformers, optimizer and schedules are splitted and instantiated like this:
### In Transformers, optimizer and schedules are splitted and instantiated like this:
optimizer=AdamW(model.parameters(),lr=lr,correct_bias=False)# To reproduce BertAdam specific behavior set correct_bias=False
