Added supported model to AutoModelTokenClassification

transformers/__init__.py

@@ -69,7 +69,7 @@ from .configuration_camembert import CamembertConfig, CAMEMBERT_PRETRAINED_CONFI
 if is_torch_available():
     from .modeling_utils import (PreTrainedModel, prune_layer, Conv1D)
     from .modeling_auto import (AutoModel, AutoModelForSequenceClassification, AutoModelForQuestionAnswering,
-                                AutoModelWithLMHead)
+                                AutoModelWithLMHead, AutoModelForTokenClassification)
 
     from .modeling_bert import (BertPreTrainedModel, BertModel, BertForPreTraining,
                                 BertForMaskedLM, BertForNextSentencePrediction,
@@ -124,7 +124,7 @@ if is_torch_available():
 if is_tf_available():
     from .modeling_tf_utils import TFPreTrainedModel, TFSharedEmbeddings, TFSequenceSummary, shape_list
     from .modeling_tf_auto import (TFAutoModel, TFAutoModelForSequenceClassification, TFAutoModelForQuestionAnswering,
-                                   TFAutoModelWithLMHead)
+                                   TFAutoModelWithLMHead, TFAutoModelForTokenClassification)
 
     from .modeling_tf_bert import (TFBertPreTrainedModel, TFBertMainLayer, TFBertEmbeddings,
                                    TFBertModel, TFBertForPreTraining,

transformers/modeling_auto.py

@@ -22,16 +22,19 @@ from .configuration_auto import (AlbertConfig, BertConfig, CamembertConfig, CTRL
                                  DistilBertConfig, GPT2Config, OpenAIGPTConfig, RobertaConfig,
                                  TransfoXLConfig, XLMConfig, XLNetConfig)
 
-from .modeling_bert import BertModel, BertForMaskedLM, BertForSequenceClassification, BertForQuestionAnswering
+from .modeling_bert import BertModel, BertForMaskedLM, BertForSequenceClassification, BertForQuestionAnswering, \
+    BertForTokenClassification
 from .modeling_openai import OpenAIGPTModel, OpenAIGPTLMHeadModel
 from .modeling_gpt2 import GPT2Model, GPT2LMHeadModel
 from .modeling_ctrl import CTRLModel, CTRLLMHeadModel
 from .modeling_transfo_xl import TransfoXLModel, TransfoXLLMHeadModel
-from .modeling_xlnet import XLNetModel, XLNetLMHeadModel, XLNetForSequenceClassification, XLNetForQuestionAnswering
+from .modeling_xlnet import XLNetModel, XLNetLMHeadModel, XLNetForSequenceClassification, XLNetForQuestionAnswering, \
+    XLNetForTokenClassification
 from .modeling_xlm import XLMModel, XLMWithLMHeadModel, XLMForSequenceClassification, XLMForQuestionAnswering
 from .modeling_roberta import RobertaModel, RobertaForMaskedLM, RobertaForSequenceClassification
 from .modeling_distilbert import DistilBertModel, DistilBertForQuestionAnswering, DistilBertForMaskedLM, DistilBertForSequenceClassification
-from .modeling_camembert import CamembertModel, CamembertForMaskedLM, CamembertForSequenceClassification, CamembertForMultipleChoice
+from .modeling_camembert import CamembertModel, CamembertForMaskedLM, CamembertForSequenceClassification, \
+    CamembertForMultipleChoice, CamembertForTokenClassification
 from .modeling_albert import AlbertModel, AlbertForMaskedLM, AlbertForSequenceClassification, AlbertForQuestionAnswering
 
 from .modeling_utils import PreTrainedModel, SequenceSummary
@@ -699,3 +702,117 @@ class AutoModelForQuestionAnswering(object):
 
         raise ValueError("Unrecognized model identifier in {}. Should contains one of "
                          "'bert', 'xlnet', 'xlm', 'distilbert', 'albert'".format(pretrained_model_name_or_path))
+
+
+class AutoModelForTokenClassification:
+    def __init__(self):
+        raise EnvironmentError("AutoModelForTokenClassification is designed to be instantiated "
+                               "using the `AutoModelForTokenClassification.from_pretrained(pretrained_model_name_or_path)` or "
+                               "`AutoModelForTokenClassification.from_config(config)` methods.")
+
+    @classmethod
+    def from_config(cls, config):
+        r""" Instantiates one of the base model classes of the library
+        from a configuration.
+    
+            config: (`optional`) instance of a class derived from :class:`~transformers.PretrainedConfig`:
+                The model class to instantiate is selected based on the configuration class:
+                    - isInstance of `distilbert` configuration class: DistilBertModel (DistilBERT model)
+                    - isInstance of `bert` configuration class: BertModel (Bert model)
+                    - isInstance of `xlnet` configuration class: XLNetModel (XLNet model)
+                    - isInstance of `xlm` configuration class: XLMModel (XLM model)
+    
+        Examples::
+    
+            config = BertConfig.from_pretrained('bert-base-uncased')    # Download configuration from S3 and cache.
+            model = AutoModelForTokenClassification.from_config(config)  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
+        """
+        if isinstance(config, CamembertConfig):
+            return CamembertForTokenClassification(config)
+        elif isinstance(config, BertConfig):
+            return BertForTokenClassification(config)
+        elif isinstance(config, XLNetConfig):
+            return XLNetForTokenClassification(config)
+        raise ValueError("Unrecognized configuration class {}".format(config))
+    
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs):
+        r""" Instantiates one of the question answering model classes of the library
+        from a pre-trained model configuration.
+
+        The `from_pretrained()` method takes care of returning the correct model class instance
+        using pattern matching on the `pretrained_model_name_or_path` string.
+
+        The model class to instantiate is selected as the first pattern matching
+        in the `pretrained_model_name_or_path` string (in the following order):
+            - contains `distilbert`: DistilBertForTokenClassification (DistilBERT model)
+            - contains `albert`: AlbertForTokenClassification (ALBERT model)
+            - contains `bert`: BertForTokenClassification (Bert model)
+            - contains `xlnet`: XLNetForTokenClassification (XLNet model)
+            - contains `xlm`: XLMForTokenClassification (XLM model)
+
+        The model is set in evaluation mode by default using `model.eval()` (Dropout modules are deactivated)
+        To train the model, you should first set it back in training mode with `model.train()`
+
+        Params:
+            pretrained_model_name_or_path: 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/``.
+                - 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_download: (`optional`) boolean, default False:
+                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.
+
+        Examples::
+
+            model = AutoModelForTokenClassification.from_pretrained('bert-base-uncased')    # Download model and configuration from S3 and cache.
+            model = AutoModelForTokenClassification.from_pretrained('./test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
+            model = AutoModelForTokenClassification.from_pretrained('bert-base-uncased', output_attention=True)  # Update configuration during loading
+            assert model.config.output_attention == True
+            # Loading from a TF checkpoint file instead of a PyTorch model (slower)
+            config = AutoConfig.from_json_file('./tf_model/bert_tf_model_config.json')
+            model = AutoModelForTokenClassification.from_pretrained('./tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
+
+        """
+        if 'camembert' in pretrained_model_name_or_path:
+            return CamembertForTokenClassification.from_pretrained(pretrained_model_name_or_path, *model_args, **kwargs)
+        elif 'bert' in pretrained_model_name_or_path:
+            return BertForTokenClassification.from_pretrained(pretrained_model_name_or_path, *model_args, **kwargs)
+        elif 'xlnet' in pretrained_model_name_or_path:
+            return XLNetForTokenClassification.from_pretrained(pretrained_model_name_or_path, *model_args, **kwargs)
+
+        raise ValueError("Unrecognized model identifier in {}. Should contains one of "
+                         "'bert', 'xlnet', 'camembert'".format(pretrained_model_name_or_path))

transformers/modeling_tf_auto.py

@@ -22,11 +22,13 @@ from .configuration_auto import (BertConfig, CTRLConfig, DistilBertConfig,
                                  GPT2Config, OpenAIGPTConfig, RobertaConfig,
                                  TransfoXLConfig, XLMConfig, XLNetConfig)
 
-from .modeling_tf_bert import TFBertModel, TFBertForMaskedLM, TFBertForSequenceClassification, TFBertForQuestionAnswering
+from .modeling_tf_bert import TFBertModel, TFBertForMaskedLM, TFBertForSequenceClassification, \
+    TFBertForQuestionAnswering, TFBertForTokenClassification
 from .modeling_tf_openai import TFOpenAIGPTModel, TFOpenAIGPTLMHeadModel
 from .modeling_tf_gpt2 import TFGPT2Model, TFGPT2LMHeadModel
 from .modeling_tf_transfo_xl import TFTransfoXLModel, TFTransfoXLLMHeadModel
-from .modeling_tf_xlnet import TFXLNetModel, TFXLNetLMHeadModel, TFXLNetForSequenceClassification, TFXLNetForQuestionAnsweringSimple
+from .modeling_tf_xlnet import TFXLNetModel, TFXLNetLMHeadModel, TFXLNetForSequenceClassification, \
+    TFXLNetForQuestionAnsweringSimple, TFXLNetForTokenClassification
 from .modeling_tf_xlm import TFXLMModel, TFXLMWithLMHeadModel, TFXLMForSequenceClassification, TFXLMForQuestionAnsweringSimple
 from .modeling_tf_roberta import TFRobertaModel, TFRobertaForMaskedLM, TFRobertaForSequenceClassification
 from .modeling_tf_distilbert import TFDistilBertModel, TFDistilBertForQuestionAnswering, TFDistilBertForMaskedLM, TFDistilBertForSequenceClassification
@@ -668,3 +670,108 @@ class TFAutoModelForQuestionAnswering(object):
 
         raise ValueError("Unrecognized model identifier in {}. Should contains one of "
                          "'distilbert', 'bert', 'xlnet', 'xlm'".format(pretrained_model_name_or_path))
+
+
+class TFAutoModelForTokenClassification:
+    def __init__(self):
+        raise EnvironmentError("TFAutoModelForTokenClassification is designed to be instantiated "
+                               "using the `TFAutoModelForTokenClassification.from_pretrained(pretrained_model_name_or_path)` or "
+                               "`AutoModelForTokenClassification.from_config(config)` methods.")
+
+    @classmethod
+    def from_config(cls, config):
+        r""" Instantiates one of the base model classes of the library
+        from a configuration.
+
+            config: (`optional`) instance of a class derived from :class:`~transformers.PretrainedConfig`:
+                The model class to instantiate is selected based on the configuration class:
+                    - isInstance of `bert` configuration class: BertModel (Bert model)
+                    - isInstance of `xlnet` configuration class: XLNetModel (XLNet model)
+
+        Examples::
+
+            config = BertConfig.from_pretrained('bert-base-uncased')    # Download configuration from S3 and cache.
+            model = TFAutoModelForTokenClassification.from_config(config)  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
+        """
+        if isinstance(config, BertConfig):
+            return TFBertForTokenClassification(config)
+        elif isinstance(config, XLNetConfig):
+            return TFXLNetForTokenClassification(config)
+        raise ValueError("Unrecognized configuration class {}".format(config))
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs):
+        r""" Instantiates one of the question answering model classes of the library
+        from a pre-trained model configuration.
+
+        The `from_pretrained()` method takes care of returning the correct model class instance
+        using pattern matching on the `pretrained_model_name_or_path` string.
+
+        The model class to instantiate is selected as the first pattern matching
+        in the `pretrained_model_name_or_path` string (in the following order):
+            - contains `bert`: BertForTokenClassification (Bert model)
+            - contains `xlnet`: XLNetForTokenClassification (XLNet model)
+
+        The model is set in evaluation mode by default using `model.eval()` (Dropout modules are deactivated)
+        To train the model, you should first set it back in training mode with `model.train()`
+
+        Params:
+            pretrained_model_name_or_path: 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/``.
+                - 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_download: (`optional`) boolean, default False:
+                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.
+
+        Examples::
+
+            model = TFAutoModelForTokenClassification.from_pretrained('bert-base-uncased')    # Download model and configuration from S3 and cache.
+            model = TFAutoModelForTokenClassification.from_pretrained('./test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
+            model = TFAutoModelForTokenClassification.from_pretrained('bert-base-uncased', output_attention=True)  # Update configuration during loading
+            assert model.config.output_attention == True
+            # Loading from a TF checkpoint file instead of a PyTorch model (slower)
+            config = AutoConfig.from_json_file('./tf_model/bert_tf_model_config.json')
+            model = TFAutoModelForTokenClassification.from_pretrained('./tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
+
+        """
+        if 'bert' in pretrained_model_name_or_path:
+            return TFBertForTokenClassification.from_pretrained(pretrained_model_name_or_path, *model_args, **kwargs)
+        elif 'xlnet' in pretrained_model_name_or_path:
+            return TFXLNetForTokenClassification.from_pretrained(pretrained_model_name_or_path, *model_args, **kwargs)
+
+        raise ValueError("Unrecognized model identifier in {}. Should contains one of "
+                         "'bert', 'xlnet'".format(pretrained_model_name_or_path))