@@ -12,6 +12,7 @@ similar API between the different models.
| [SQuAD](#squad) | Using BERT/XLM/XLNet/RoBERTa for question answering, examples with distributed training. |
| [Multiple Choice](#multiple-choice) | Examples running BERT/XLNet/RoBERTa on the SWAG/RACE/ARC tasks.
| [Named Entity Recognition](#named-entity-recognition) | Using BERT for Named Entity Recognition (NER) on the CoNLL 2003 dataset, examples with distributed training. |
| [Abstractive summarization](#abstractive-summarization) | Fine-tuning the library models for abstractive summarization tasks on the CNN/Daily Mail dataset. |
## TensorFlow 2.0 Bert models on GLUE
...
...
@@ -411,7 +412,7 @@ f1 = 93.15
exact_match = 86.91
```
This fine-tuneds model is available as a checkpoint under the reference
This fine-tuned model is available as a checkpoint under the reference
**labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
...
...
@@ -1039,7 +1139,7 @@ class BertForTokenClassification(BertPreTrainedModel):
outputs=self.bert(input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
position_ids=position_ids,
position_ids=position_ids,
head_mask=head_mask)
sequence_output=outputs[0]
...
...
@@ -1064,8 +1164,9 @@ class BertForTokenClassification(BertPreTrainedModel):
@add_start_docstrings("""Bert Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of
the hidden-states output to compute `span start logits` and `span end logits`). """,
BERT_START_DOCSTRING,BERT_INPUTS_DOCSTRING)
the hidden-states output to compute `span start logits` and `span end logits`). """,
:class:`~transformers.PreTrainedEncoderDecoder` is a generic model class that will be
instantiated as a transformer architecture with one of the base model
classes of the library as encoder and (optionally) another one as
decoder when created with the `AutoModel.from_pretrained(pretrained_model_name_or_path)`
class method.
"""
def__init__(self,encoder,decoder):
super(PreTrainedEncoderDecoder,self).__init__()
self.encoder=encoder
self.decoder=decoder
@classmethod
deffrom_pretrained(
cls,
encoder_pretrained_model_name_or_path=None,
decoder_pretrained_model_name_or_path=None,
*model_args,
**kwargs
):
r""" Instantiates an encoder and a decoder from one or two base classes of the library from pre-trained model checkpoints.
The model is set in evaluation mode by default using `model.eval()` (Dropout modules are deactivated)
To train the model, you need to first set it back in training mode with `model.train()`
Params:
encoder_pretrained_model_name_or_path: information necessary to initiate the encoder. Either:
- a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
- a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/encoder``.
- a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
decoder_pretrained_model_name_or_path: information necessary to initiate the decoder. Either:
- a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
- a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/decoder``.
- a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
model_args: (`optional`) Sequence of positional arguments:
All remaning positional arguments will be passed to the underlying model's ``__init__`` method
config: (`optional`) instance of a class derived from :class:`~transformers.PretrainedConfig`:
Configuration for the model to use instead of an automatically loaded configuation. Configuration can be automatically loaded when:
- the model is a model provided by the library (loaded with the ``shortcut-name`` string of a pretrained model), or
- the model was saved using :func:`~transformers.PreTrainedModel.save_pretrained` and is reloaded by suppling the save directory.
- the model is loaded by suppling a local directory as ``pretrained_model_name_or_path`` and a configuration JSON file named `config.json` is found in the directory.
state_dict: (`optional`) dict:
an optional state dictionnary for the model to use instead of a state dictionary loaded from saved weights file.
This option can be used if you want to create a model from a pretrained configuration but load your own weights.
In this case though, you should check if using :func:`~transformers.PreTrainedModel.save_pretrained` and :func:`~transformers.PreTrainedModel.from_pretrained` is not a simpler option.
cache_dir: (`optional`) string:
Path to a directory in which a downloaded pre-trained model
configuration should be cached if the standard cache should not be used.
Force to (re-)download the model weights and configuration files and override the cached versions if they exists.
proxies: (`optional`) dict, default None:
A dictionary of proxy servers to use by protocol or endpoint, e.g.: {'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}.
The proxies are used on each request.
output_loading_info: (`optional`) boolean:
Set to ``True`` to also return a dictionnary containing missing keys, unexpected keys and error messages.
kwargs: (`optional`) Remaining dictionary of keyword arguments.
Can be used to update the configuration object (after it being loaded) and initiate the model. (e.g. ``output_attention=True``). Behave differently depending on whether a `config` is provided or automatically loaded:
- If a configuration is provided with ``config``, ``**kwargs`` will be directly passed to the underlying model's ``__init__`` method (we assume all relevant updates to the configuration have already been done)
- If a configuration is not provided, ``kwargs`` will be first passed to the configuration class initialization function (:func:`~transformers.PretrainedConfig.from_pretrained`). Each key of ``kwargs`` that corresponds to a configuration attribute will be used to override said attribute with the supplied ``kwargs`` value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model's ``__init__`` function.
You can specify kwargs sepcific for the encoder and decoder by prefixing the key with `encoder_` and `decoder_` respectively. (e.g. ``decoder_output_attention=True``). The remaining kwargs will be passed to both encoders and decoders.
Examples::
model = PreTrainedEncoderDecoder.from_pretained('bert-base-uncased', 'bert-base-uncased') # initialize Bert2Bert
"""
# keyword arguments come in 3 flavors: encoder-specific (prefixed by
# `encoder_`), decoder-specific (prefixed by `decoder_`) and those
# that apply to the model as a whole.
# We let the specific kwargs override the common ones in case of conflict.
kwargs_common={
argument:value
forargument,valueinkwargs.items()
ifnotargument.startswith("encoder_")
andnotargument.startswith("decoder_")
}
kwargs_decoder=kwargs_common.copy()
kwargs_encoder=kwargs_common.copy()
kwargs_encoder.update(
{
argument[len("encoder_"):]:value
forargument,valueinkwargs.items()
ifargument.startswith("encoder_")
}
)
kwargs_decoder.update(
{
argument[len("decoder_"):]:value
forargument,valueinkwargs.items()
ifargument.startswith("decoder_")
}
)
# Load and initialize the encoder and decoder
# The distinction between encoder and decoder at the model level is made
# by the value of the flag `is_decoder` that we need to set correctly.
