change mention of decoder_input_ids to input_ids and same with decode_inputs_embeds (#26406)

* change mention of decoder_input_ids to input_ids and same with decoder_input_embeds

* Style

---------
Co-authored-by: Lysandre <lysandre@huggingface.co>

src/transformers/models/llama/modeling_llama.py

@@ -722,7 +722,7 @@ LLAMA_INPUTS_DOCSTRING = r"""
             Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
             [`PreTrainedTokenizer.__call__`] for details.
 
-            If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see
+            If `past_key_values` is used, optionally only the last `input_ids` have to be input (see
             `past_key_values`).
 
             If you want to change padding behavior, you should read [`modeling_opt._prepare_decoder_attention_mask`]
@@ -744,9 +744,9 @@ LLAMA_INPUTS_DOCSTRING = r"""
             Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
             blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
 
-            If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
-            don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
-            `decoder_input_ids` of shape `(batch_size, sequence_length)`.
+            If `past_key_values` are used, the user can optionally input only the last `input_ids` (those that don't
+            have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `input_ids`
+            of shape `(batch_size, sequence_length)`.
         inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
             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
@@ -843,13 +843,13 @@ class LlamaModel(LlamaPreTrainedModel):
 
         # retrieve input_ids and inputs_embeds
         if input_ids is not None and inputs_embeds is not None:
-            raise ValueError("You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time")
+            raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             batch_size, seq_length = input_ids.shape
         elif inputs_embeds is not None:
             batch_size, seq_length, _ = inputs_embeds.shape
         else:
-            raise ValueError("You have to specify either decoder_input_ids or decoder_inputs_embeds")
+            raise ValueError("You have to specify either input_ids or inputs_embeds")
 
         seq_length_with_past = seq_length
         past_key_values_length = 0