[inputs_embeds] All PyTorch models

transformers/modeling_tf_gpt2.py

@@ -408,6 +408,10 @@ GPT2_INPUTS_DOCSTRING = r"""    Inputs:
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
+        **inputs_embeds**: (`optional`) ``Numpy array`` or ``tf.Tensor`` of shape ``(batch_size, sequence_length, embedding_dim)``:
+            Optionally, instead of passing ``input_ids`` you can choose to directly pass an embedded representation.
+            This is useful if you want more control over how to convert `input_ids` indices into associated vectors
+            than the model's internal embedding lookup matrix.
 """
 
 @add_start_docstrings("The bare GPT2 Model transformer outputing raw hidden-states without any specific head on top.",