Update modeling_phi3.py

modeling_phi3.py

@@ -1294,10 +1294,6 @@ class Phi3ForCausalLM(Phi3PreTrainedModel):
                 cache_length = past_length = past_key_values[0][0].shape[2]
                 max_cache_length = None
 
-            else:
-                cache_length = past_length = past_key_values[0][0].shape[2]
-                max_cache_length = None
-
             # Keep only the unprocessed tokens:
             # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
             # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
@@ -1564,4 +1560,4 @@ class Phi3ForTokenClassification(Phi3PreTrainedModel):
             logits=logits,
             hidden_states=model_outputs.hidden_states,
             attentions=model_outputs.attentions,
-        )
+        )