Metadata-Version: 2.1
Name: bert4tf
Version: 2.0.2
Summary: bert for tensorflow2
Home-page: https://github.com/charlesXu86/Bert4tf
Author: xu
Author-email: charlesxu86@163.com
License: MIT Licence
Keywords: bert4tf,tensorflow2
Platform: any
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.6
Description-Content-Type: text/x-rst
Requires-Dist: tensorflow

BERT for TensorFlow v2
======================

This repo contains a `TensorFlow 2.0`_ `Keras`_ implementation of `google-research/bert`_
with support for loading of the original `pre-trained weights`_,
and producing activations **numerically identical** to the one calculated by the original model.

`ALBERT`_ and `adapter-BERT`_ are also supported by setting the corresponding
configuration parameters (``shared_layer=True``, ``embedding_size`` for `ALBERT`_
and ``adapter_size`` for `adapter-BERT`_). Setting both will result in an adapter-ALBERT
by sharing the BERT parameters across all layers while adapting every layer with layer specific adapter.

The implementation is build from scratch using only basic tensorflow operations,
following the code in `google-research/bert/modeling.py`_
(but skipping dead code and applying some simplifications). It also utilizes `kpe/params-flow`_ to reduce
common Keras boilerplate code (related to passing model and layer configuration arguments).

`bert4tf`_ should work with both `TensorFlow 2.0`_ and `TensorFlow 1.14`_ or newer.

NEWS
----


LICENSE
-------

MIT. See `License File <https://github.com/kpe/bert-for-tf2/blob/master/LICENSE.txt>`_.

Install
-------

``bert4tf`` is on the Python Package Index (PyPI):

::

    pip install bert4tf


Usage
-----

BERT in `bert4tf` is implemented as a Keras layer. You could instantiate it like this:

.. code:: python

  from bert4tf import BertModelLayer

  l_bert = BertModelLayer(**BertModelLayer.Params(
    vocab_size               = 16000,        # embedding params
    use_token_type           = True,
    use_position_embeddings  = True,
    token_type_vocab_size    = 2,

    num_layers               = 12,           # transformer encoder params
    hidden_size              = 768,
    hidden_dropout           = 0.1,
    intermediate_size        = 4*768,
    intermediate_activation  = "gelu",

    adapter_size             = None,         # see arXiv:1902.00751 (adapter-BERT)

    shared_layer             = False,        # True for ALBERT (arXiv:1909.11942)
    embedding_size           = None,         # None for BERT, wordpiece embedding size for ALBERT

    name                     = "bert"        # any other Keras layer params
  ))

or by using the ``bert_config.json`` from a `pre-trained google model`_:

.. code:: python

  import bert4tf

  model_dir = ".models/uncased_L-12_H-768_A-12"

  bert_params = bert.params_from_pretrained_ckpt(model_dir)
  l_bert = bert4tf.BertModelLayer.from_params(bert_params, name="bert")


now you can use the BERT layer in your Keras model like this:

.. code:: python

  from tensorflow import keras

  max_seq_len = 128
  l_input_ids      = keras.layers.Input(shape=(max_seq_len,), dtype='int32')
  l_token_type_ids = keras.layers.Input(shape=(max_seq_len,), dtype='int32')

  # using the default token_type/segment id 0
  output = l_bert(l_input_ids)                              # output: [batch_size, max_seq_len, hidden_size]
  model = keras.Model(inputs=l_input_ids, outputs=output)
  model.build(input_shape=(None, max_seq_len))

  # provide a custom token_type/segment id as a layer input
  output = l_bert([l_input_ids, l_token_type_ids])          # [batch_size, max_seq_len, hidden_size]
  model = keras.Model(inputs=[l_input_ids, l_token_type_ids], outputs=output)
  model.build(input_shape=[(None, max_seq_len), (None, max_seq_len)])

if you choose to use `adapter-BERT`_ by setting the `adapter_size` parameter,
you would also like to freeze all the original BERT layers by calling:

.. code:: python

  l_bert.apply_adapter_freeze()

and once the model has been build or compiled, the original pre-trained weights
can be loaded in the BERT layer:

.. code:: python

  import bert4tf

  bert_ckpt_file   = os.path.join(model_dir, "bert_model.ckpt")
  bert.load_stock_weights(l_bert, bert_ckpt_file)

**N.B.** see `tests/test_bert_activations.py`_ for a complete example.

FAQ
---
1. How to use BERT with the `google-research/bert`_ pre-trained weights?

.. code:: python

  model_name = "uncased_L-12_H-768_A-12"
  model_dir = bert4tf.fetch_google_bert_model(model_name, ".models")
  model_ckpt = os.path.join(model_dir, "bert_model.ckpt")

  bert_params = bert4tf.params_from_pretrained_ckpt(model_dir)
  l_bert = bert4tf.BertModelLayer.from_params(bert_params, name="bert")

  # use in Keras Model here, and call model.build()

  bert.load_bert_weights(l_bert, model_ckpt)      # should be called after model.build()

2. How to use ALBERT with the `google-research/albert`_ pre-trained weights?

.. code:: python

  model_name = "albert_base"
  model_dir    = bert4tf.fetch_tfhub_albert_model(model_name, ".models")
  model_params = bert4tf.albert_params(model_name)
  l_bert = bert.BertModelLayer.from_params(model_params, name="albert")

  # use in Keras Model here, and call model.build()

  bert.load_albert_weights(l_bert, albert_dir)      # should be called after model.build()

3. How to use ALBERT with the `albert_zh` pre-trained weights?

see `tests/nonci/test_albert.py <https://github.com/kpe/bert-for-tf2/blob/master/tests/nonci/test_albert.py>`_:

.. code:: python

  model_name = "albert_base"
  model_dir = bert4tf.fetch_brightmart_albert_model(model_name, ".models")
  model_ckpt = os.path.join(model_dir, "albert_model.ckpt")

  bert_params = bert.params_from_pretrained_ckpt(model_dir)
  l_bert = bert.BertModelLayer.from_params(bert_params, name="bert")

  # use in a Keras Model here, and call model.build()

  bert.load_albert_weights(l_bert, model_ckpt)      # should be called after model.build()

4. How to tokenize the input for the `google-research/bert`_ models?

  do_lower_case = not (model_name.find("cased") == 0 or model_name.find("multi_cased") == 0)
  bert.bert_tokenization.validate_case_matches_checkpoint(do_lower_case, model_ckpt)
  vocab_file = os.path.join(model_dir, "vocab.txt")
  tokenizer = bert4tf.bert_tokenization.FullTokenizer(vocab_file, do_lower_case)
  tokens = tokenizer.tokenize("Hello, BERT-World!")
  token_ids = tokenizer.convert_tokens_to_ids(tokens)

5. How to tokenize the input for the `google-research/albert`_ models?

  import sentencepiece as spm

  spm_model = os.path.join(model_dir, "assets", "30k-clean.model")
  sp = spm.SentencePieceProcessor()
  sp.load(spm_model)
  do_lower_case = True

  processed_text = bert.albert_tokenization.preprocess_text("Hello, World!", lower=do_lower_case)
  token_ids = bert4tf.albert_tokenization.encode_ids(sp, processed_text)


Referrence
---
1. kpe

Resources
---------

- `BERT`_ - BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- `adapter-BERT`_ - adapter-BERT: Parameter-Efficient Transfer Learning for NLP
- `ALBERT`_ - ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations
- `google-research/bert`_ - the original `BERT`_ implementation
- `google-research/albert`_ - the original `ALBERT`_ implementation by Google
- `kpe/params-flow`_ - A Keras coding style for reducing `Keras`_ boilerplate code in custom layers by utilizing `kpe/py-params`_

.. _`kpe/params-flow`: https://github.com/kpe/params-flow
.. _`kpe/py-params`: https://github.com/kpe/py-params
.. _`bert4tf`: https://github.com/charlesXu86/Bert4tf

.. _`Keras`: https://keras.io
.. _`pre-trained weights`: https://github.com/google-research/bert#pre-trained-models
.. _`google-research/bert`: https://github.com/google-research/bert
.. _`google-research/bert/modeling.py`: https://github.com/google-research/bert/blob/master/modeling.py
.. _`BERT`: https://arxiv.org/abs/1810.04805
.. _`pre-trained google model`: https://github.com/google-research/bert
.. _`tests/test_bert_activations.py`: https://github.com/kpe/bert-for-tf2/blob/master/tests/test_compare_activations.py
.. _`TensorFlow 2.0`: https://www.tensorflow.org/versions/r2.0/api_docs/python/tf
.. _`TensorFlow 1.14`: https://www.tensorflow.org/versions/r1.14/api_docs/python/tf

.. _`google-research/adapter-bert`: https://github.com/google-research/adapter-bert/
.. _`adapter-BERT`: https://arxiv.org/abs/1902.00751
.. _`ALBERT`: https://arxiv.org/abs/1909.11942
.. _`google ALBERT weights`: https://github.com/google-research/google-research/tree/master/albert
.. _`google-research/albert`: https://github.com/google-research/google-research/tree/master/albert
.. _`TFHub/albert`: https://tfhub.dev/google/albert_base/1

