Update modeling_hyena.py

modeling_hyena.py

@@ -463,7 +463,7 @@ class HyenaDNAForCausalLM(HyenaDNAPreTrainedModel):
             shift_labels = labels[..., 1:].contiguous()
             # Flatten the tokens
             loss_fct = nn.CrossEntropyLoss()
-            shift_logits = shift_logits.view(-1, self.config.vocab_size)
+            shift_logits = shift_logits.view(-1, self.vocab_size)
             shift_labels = shift_labels.view(-1)
             # Enable model parallelism
             shift_labels = shift_labels.to(shift_logits.device)