Update modeling_chatglm.py

modeling_chatglm.py

@@ -255,7 +255,7 @@ class CoreAttention(torch.nn.Module):
             # [sk, b, np, hn] --> [b, np, sq, hn]
 
             # context layer shape: [b, np, sq, hn]
-            output_size = (value_layer.size(1), value_layer.size(2), query_layer.size(0), value_layer.size(3))
+            output_size = (value_layer.size(0), value_layer.size(1), query_layer.size(1), value_layer.size(3))
             # change view [b * np, sk, hn]
             value_layer = value_layer.view(output_size[0] * output_size[1], value_layer.size(2), -1)
             # change view [b * np, sq, sk]