Repo consistency

src/transformers/models/biogpt/modeling_biogpt.py

@@ -153,7 +153,14 @@ class BioGptAttention(nn.Module):
         # get query proj
         query_states = self.q_proj(hidden_states) * self.scaling
         # get key, value proj
-        if is_cross_attention and past_key_value is not None:
+        # `past_key_value[0].shape[2] == key_value_states.shape[1]`
+        # is checking that the `sequence_length` of the `past_key_value` is the same as
+        # the provided `key_value_states` to support prefix tuning
+        if (
+            is_cross_attention
+            and past_key_value is not None
+            and past_key_value[0].shape[2] == key_value_states.shape[1]
+        ):
             # reuse k,v, cross_attentions
             key_states = past_key_value[0]
             value_states = past_key_value[1]