fix encoder decoder

modeling_lsg_bart.py

@@ -998,7 +998,7 @@ class LSGBartModel(LSGBartPretrainedModel, BartModel):
             )
 
         # Pad mask for global tokens
-        if self.pass_global_tokens_to_decoder:
+        if self.pass_global_tokens_to_decoder and attention_mask is not None:
             attention_mask = torch.nn.functional.pad(attention_mask, pad=(self.num_global_tokens, 0), value=1)
             
         # decoder outputs consists of (dec_features, past_key_value, dec_hidden, dec_attn)