Update modeling_chatglm.py

modeling_chatglm.py

@@ -762,6 +762,8 @@ class GLMTransformer(torch.nn.Module):
     ):
         if not kv_caches:
             kv_caches = [None for _ in range(self.num_layers)]
+        else:
+            kv_caches=kv_caches[1]
         presents = () if use_cache else None
         if self.gradient_checkpointing and self.training:
             if use_cache: