Add position_ids (#5021)

src/transformers/modeling_tf_electra.py

@@ -336,6 +336,11 @@ ELECTRA_INPUTS_DOCSTRING = r"""
             ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
+        position_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`{0}`, `optional`, defaults to :obj:`None`):
+            Indices of positions of each input sequence tokens in the position embeddings.
+            Selected in the range ``[0, config.max_position_embeddings - 1]``.
+
+            `What are position IDs? <../glossary.html#position-ids>`__
         head_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`, defaults to :obj:`None`):
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``: