Update modeling_florence2.py

modeling_florence2.py

@@ -2240,6 +2240,10 @@ class Florence2Seq2SeqLMOutput(ModelOutput):
     decoding.
 
     Args:
+        loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
+            Language modeling loss.
+        logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
+            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
             Sequence of hidden-states at the output of the last layer of the decoder of the model.
 
@@ -2289,6 +2293,7 @@ class Florence2Seq2SeqLMOutput(ModelOutput):
             image_hidden_states of the model produced by the vision encoder
     """
     loss: Optional[torch.FloatTensor] = None
+    logits: torch.FloatTensor = None
     last_hidden_state: torch.FloatTensor = None
     past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None
     decoder_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
@@ -2297,7 +2302,6 @@ class Florence2Seq2SeqLMOutput(ModelOutput):
     encoder_last_hidden_state: Optional[torch.FloatTensor] = None
     encoder_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
     encoder_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
-    logits: torch.FloatTensor = None
     image_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None