camembert: add wrapper for CamembertForTokenClassification

transformers/modeling_camembert.py

@@ -20,7 +20,7 @@ from __future__ import (absolute_import, division, print_function,
 
 import logging
 
-from .modeling_roberta import RobertaModel, RobertaForMaskedLM, RobertaForSequenceClassification, RobertaForMultipleChoice
+from .modeling_roberta import RobertaModel, RobertaForMaskedLM, RobertaForSequenceClassification, RobertaForMultipleChoice, RobertaForTokenClassification
 from .configuration_camembert import CamembertConfig
 from .file_utils import add_start_docstrings
 
@@ -255,3 +255,39 @@ class CamembertForMultipleChoice(RobertaForMultipleChoice):
     """
     config_class = CamembertConfig
     pretrained_model_archive_map = CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP
+
+
+@add_start_docstrings("""CamemBERT Model with a token classification head on top (a linear layer on top of
+    the hidden-states output) e.g. for Named-Entity-Recognition (NER) tasks. """,
+    CAMEMBERT_START_DOCSTRING, CAMEMBERT_INPUTS_DOCSTRING)
+class CamembertForTokenClassification(RobertaForTokenClassification):
+    r"""
+        **labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
+            Labels for computing the token classification loss.
+            Indices should be in ``[0, ..., config.num_labels - 1]``.
+
+    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
+        **loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
+            Classification loss.
+        **scores**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, config.num_labels)``
+            Classification scores (before SoftMax).
+        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
+            list of ``torch.FloatTensor`` (one for the output of each layer + the output of the embeddings)
+            of shape ``(batch_size, sequence_length, hidden_size)``:
+            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
+        **attentions**: (`optional`, returned when ``config.output_attentions=True``)
+            list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
+            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
+
+    Examples::
+
+        tokenizer = CamembertTokenizer.from_pretrained('camembert-base')
+        model = CamembertForTokenClassification.from_pretrained('camembert-base')
+        input_ids = torch.tensor(tokenizer.encode("J'aime le camembert !", add_special_tokens=True)).unsqueeze(0)  # Batch size 1
+        labels = torch.tensor([1] * input_ids.size(1)).unsqueeze(0)  # Batch size 1
+        outputs = model(input_ids, labels=labels)
+        loss, scores = outputs[:2]
+
+    """
+    config_class = CamembertConfig
+    pretrained_model_archive_map = CAMEMBERT_PRETRAINED_MODEL_ARCHIVE_MAP