SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Clean up autoclass doc (#7081)

Browse Source
This commit is contained in:
Sylvain Gugger
2020-09-14 09:26:41 -04:00
committed by GitHub
parent 3ca1874ca4
commit ccc8e30c8a
5 changed files with 1077 additions and 1609 deletions
Download Patch File Download Diff File Expand all files Collapse all files

105
src/transformers/configuration_auto.py
View File

@@ -197,9 +197,7 @@ class AutoConfig:
This is a generic configuration class that will be instantiated as one of the configuration classes of the library
when created with the :meth:`~transformers.AutoConfig.from_pretrained` class method.
This method takes care of returning the correct model class instance
based on the `model_type` property of the config object, or when it's missing,
falling back to using pattern matching on the `pretrained_model_name_or_path` string.
This class cannot be instantiated directly using ``__init__()`` (throws an error).
"""
def __init__(self):
@@ -222,58 +220,77 @@ class AutoConfig:
@classmethod
@replace_list_option_in_docstrings()
def from_pretrained(cls, pretrained_model_name_or_path, **kwargs):
r""" Instantiates one of the configuration classes of the library
from a pre-trained model configuration.
r"""
Instantiate one of the configuration classes of the library from a pretrained model configuration.
The configuration class to instantiate is selected
based on the `model_type` property of the config object, or when it's missing,
falling back to using pattern matching on the `pretrained_model_name_or_path` string:
The configuration class to instantiate is selected based on the :obj:`model_type` property of the config
object that is loaded, or when it's missing, by falling back to using pattern matching on
:obj:`pretrained_model_name_or_path`:
List options
Args:
pretrained_model_name_or_path (:obj:`string`):
Is either: \
- a string with the `shortcut name` of a pre-trained model configuration to load from cache or download, e.g.: ``bert-base-uncased``.
- a string with the `identifier name` of a pre-trained model configuration that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
- a path to a `directory` containing a configuration file saved using the :func:`~transformers.PretrainedConfig.save_pretrained` method, e.g.: ``./my_model_directory/``.
- a path or url to a saved configuration JSON `file`, e.g.: ``./my_model_directory/configuration.json``.
pretrained_model_name_or_path (:obj:`str`):
Can be either:
cache_dir (:obj:`string`, optional, defaults to `None`):
Path to a directory in which a downloaded pre-trained model
configuration should be cached if the standard cache should not be used.
force_download (:obj:`boolean`, optional, defaults to `False`):
Force to (re-)download the model weights and configuration files and override the cached versions if they exist.
resume_download (:obj:`boolean`, optional, defaults to `False`):
Do not delete incompletely received file. Attempt to resume the download if such a file exists.
proxies (:obj:`Dict[str, str]`, optional, defaults to `None`):
A dictionary of proxy servers to use by protocol or endpoint, e.g.: :obj:`{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}`.
The proxies are used on each request. See `the requests documentation <https://requests.readthedocs.io/en/master/user/advanced/#proxies>`__ for usage.
return_unused_kwargs (:obj:`boolean`, optional, defaults to `False`):
- If False, then this function returns just the final configuration object.
- If True, then this functions returns a tuple `(config, unused_kwargs)` where `unused_kwargs` is a dictionary consisting of the key/value pairs whose keys are not configuration attributes: ie the part of kwargs which has not been used to update `config` and is otherwise ignored.
kwargs (:obj:`Dict[str, any]`, optional, defaults to `{}`): key/value pairs with which to update the configuration object after loading.
- The values in kwargs of any keys which are configuration attributes will be used to override the loaded values.
- Behavior concerning key/value pairs whose keys are *not* configuration attributes is controlled by the `return_unused_kwargs` keyword parameter.
- A string with the `shortcut name` of a pretrained model configuration to load from cache or
download, e.g., ``bert-base-uncased``.
- A string with the `identifier name` of a pretrained model configuration that was user-uploaded to
our S3, e.g., ``dbmdz/bert-base-german-cased``.
- A path to a `directory` containing a configuration file saved using the
:meth:`~transformers.PretrainedConfig.save_pretrained` method, or the
:meth:`~transformers.PretrainedModel.save_pretrained` method, e.g., ``./my_model_directory/``.
- A path or url to a saved configuration JSON `file`, e.g.,
``./my_model_directory/configuration.json``.
cache_dir (:obj:`str`, `optional`):
Path to a directory in which a downloaded pretrained model configuration should be cached if the
standard cache should not be used.
force_download (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether or not to force the (re-)download the model weights and configuration files and override the
cached versions if they exist.
resume_download (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether or not to delete incompletely received files. Will attempt to resume the download if such a
file exists.
proxies (:obj:`Dict[str, str]`, `optional`):
A dictionary of proxy servers to use by protocol or endpoint, e.g.,
:obj:`{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}`. The proxies are used on each
request.
return_unused_kwargs (:obj:`bool`, `optional`, defaults to :obj:`False`):
If :obj:`False`, then this function returns just the final configuration object.
If :obj:`True`, then this functions returns a :obj:`Tuple(config, unused_kwargs)` where `unused_kwargs`
is a dictionary consisting of the key/value pairs whose keys are not configuration attributes: i.e.,
the part of ``kwargs`` which has not been used to update ``config`` and is otherwise ignored.
kwargs(additional keyword arguments, `optional`):
The values in kwargs of any keys which are configuration attributes will be used to override the loaded
values. Behavior concerning key/value pairs whose keys are *not* configuration attributes is
controlled by the ``return_unused_kwargs`` keyword parameter.
Examples::
config = AutoConfig.from_pretrained('bert-base-uncased') # Download configuration from S3 and cache.
config = AutoConfig.from_pretrained('./test/bert_saved_model/') # E.g. config (or model) was saved using `save_pretrained('./test/saved_model/')`
config = AutoConfig.from_pretrained('./test/bert_saved_model/my_configuration.json')
config = AutoConfig.from_pretrained('bert-base-uncased', output_attentions=True, foo=False)
assert config.output_attentions == True
config, unused_kwargs = AutoConfig.from_pretrained('bert-base-uncased', output_attentions=True,
foo=False, return_unused_kwargs=True)
assert config.output_attentions == True
assert unused_kwargs == {'foo': False}
>>> from transformers import AutoConfig
>>> # Download configuration from S3 and cache.
>>> config = AutoConfig.from_pretrained('bert-base-uncased')
>>> # Download configuration from S3 (user-uploaded) and cache.
>>> config = AutoConfig.from_pretrained('dbmdz/bert-base-german-cased')
>>> # If configuration file is in a directory (e.g., was saved using `save_pretrained('./test/saved_model/')`).
>>> config = AutoConfig.from_pretrained('./test/bert_saved_model/')
>>> # Load a specific configuration file.
>>> config = AutoConfig.from_pretrained('./test/bert_saved_model/my_configuration.json')
>>> # Change some config attributes when loading a pretrained config.
>>> config = AutoConfig.from_pretrained('bert-base-uncased', output_attentions=True, foo=False)
>>> config.output_attentions
True
>>> config, unused_kwargs = AutoConfig.from_pretrained('bert-base-uncased', output_attentions=True, foo=False, return_unused_kwargs=True)
>>> config.output_attentions
True
>>> config.unused_kwargs
{'foo': False}
"""
config_dict, _ = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)

1096
src/transformers/modeling_auto.py
View File

File diff suppressed because it is too large Load Diff

1297
src/transformers/modeling_tf_auto.py
View File

File diff suppressed because it is too large Load Diff

86
src/transformers/tokenization_auto.py
View File

@@ -117,12 +117,11 @@ SLOW_TOKENIZER_MAPPING = {k: v[0] for k, v in TOKENIZER_MAPPING.items()}
class AutoTokenizer:
r""":class:`~transformers.AutoTokenizer` is a generic tokenizer class
that will be instantiated as one of the tokenizer classes of the library
when created with the `AutoTokenizer.from_pretrained(pretrained_model_name_or_path)`
class method.
r"""
This is a generic tokenizer class that will be instantiated as one of the tokenizer classes of the library
when created with the :meth:`AutoTokenizer.from_pretrained` class method.
This class cannot be instantiated using `__init__()` (throw an error).
This class cannot be instantiated directly using ``__init__()`` (throws an error).
"""
def __init__(self):
@@ -134,45 +133,57 @@ class AutoTokenizer:
@classmethod
@replace_list_option_in_docstrings(SLOW_TOKENIZER_MAPPING)
def from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs):
r"""Instantiate one of the tokenizer classes of the library
from a pre-trained model vocabulary.
r"""
Instantiate one of the tokenizer classes of the library from a pretrained model vocabulary.
The tokenizer class to instantiate is selected
based on the `model_type` property of the config object, or when it's missing,
falling back to using pattern matching on the `pretrained_model_name_or_path` string:
The tokenizer class to instantiate is selected based on the :obj:`model_type` property of the config object
(either passed as an argument or loaded from :obj:`pretrained_model_name_or_path` if possible), or when it's
missing, by falling back to using pattern matching on :obj:`pretrained_model_name_or_path`:
List options
Params:
pretrained_model_name_or_path: either:
pretrained_model_name_or_path (:obj:`str`):
Can be either:
- a string with the `shortcut name` of a predefined tokenizer to load from cache or download, e.g.: ``bert-base-uncased``.
- a string with the `identifier name` of a predefined tokenizer that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
- a path to a `directory` containing vocabulary files required by the tokenizer, for instance saved using the :func:`~transformers.PreTrainedTokenizer.save_pretrained` method, e.g.: ``./my_model_directory/``.
- (not applicable to all derived classes) a path or url to a single saved vocabulary file if and only if the tokenizer only requires a single vocabulary file (e.g. Bert, XLNet), e.g.: ``./my_model_directory/vocab.txt``.
cache_dir: (`optional`) string:
Path to a directory in which a downloaded predefined tokenizer vocabulary files should be cached if the standard cache should not be used.
force_download: (`optional`) boolean, default False:
Force to (re-)download the vocabulary files and override the cached versions if they exists.
resume_download: (`optional`) boolean, default False:
Do not delete incompletely recieved file. Attempt to resume the download if such a file 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.
use_fast: (`optional`) boolean, default False:
Indicate if transformers should try to load the fast version of the tokenizer (True) or use the Python one (False).
inputs: (`optional`) positional arguments: will be passed to the Tokenizer ``__init__`` method.
kwargs: (`optional`) keyword arguments: will be passed to the Tokenizer ``__init__`` method. Can be used to set special tokens like ``bos_token``, ``eos_token``, ``unk_token``, ``sep_token``, ``pad_token``, ``cls_token``, ``mask_token``, ``additional_special_tokens``. See parameters in the doc string of :class:`~transformers.PreTrainedTokenizer` for details.
- A string with the `shortcut name` of a predefined tokenizer to load from cache or download, e.g.,
``bert-base-uncased``.
- A string with the `identifier name` of a predefined tokenizer that was user-uploaded to our S3,
e.g., ``dbmdz/bert-base-german-cased``.
- A path to a `directory` containing vocabulary files required by the tokenizer, for instance saved
using the :func:`~transformers.PreTrainedTokenizer.save_pretrained` method, e.g.,
``./my_model_directory/``.
- A path or url to a single saved vocabulary file if and only if the tokenizer only requires a
single vocabulary file (like Bert or XLNet), e.g.: ``./my_model_directory/vocab.txt``.
(Not applicable to all derived classes)
inputs (additional positional arguments, `optional`):
Will be passed along to the Tokenizer ``__init__()`` method.
config (:class:`~transformers.PreTrainedConfig`, `optional`)
The configuration object used to dertermine the tokenizer class to instantiate.
cache_dir (:obj:`str`, `optional`):
Path to a directory in which a downloaded pretrained model configuration should be cached if the
standard cache should not be used.
force_download (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether or not to force the (re-)download the model weights and configuration files and override the
cached versions if they exist.
resume_download (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether or not to delete incompletely received files. Will attempt to resume the download if such a
file exists.
proxies (:obj:`Dict[str, str]`, `optional`):
A dictionary of proxy servers to use by protocol or endpoint, e.g.,
:obj:`{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}`. The proxies are used on each
request.
use_fast (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether or not to try to load the fast version of the tokenizer.
kwargs (additional keyword arguments, `optional`):
Will be passed to the Tokenizer ``__init__()`` method. Can be used to set special tokens like
``bos_token``, ``eos_token``, ``unk_token``, ``sep_token``, ``pad_token``, ``cls_token``,
``mask_token``, ``additional_special_tokens``. See parameters in the ``__init__()`` for more details.
Examples::
from transformers import AutoTokenizer
# Download vocabulary from S3 and cache.
tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
@@ -208,7 +219,10 @@ class AutoTokenizer:
if isinstance(config, EncoderDecoderConfig):
if type(config.decoder) is not type(config.encoder): # noqa: E721
logger.warn(
f"The encoder model config class: {config.encoder.__class__} is different from the decoder model config class: {config.decoder.__class}. It is not recommended to use the `AutoTokenizer.from_pretrained(..)` method in this case. Please use the encoder and decoder specific tokenizer classes."
f"The encoder model config class: {config.encoder.__class__} is different from the decoder model "
f"config class: {config.decoder.__class}. It is not recommended to use the "
"`AutoTokenizer.from_pretrained()` method in this case. Please use the encoder and decoder "
"specific tokenizer classes."
)
config = config.encoder