[legacy] clean up legacy code (#4743)

* [legacy] remove outdated codes of pipeline (#4692)

* [legacy] remove cli of benchmark and update optim (#4690)

* [legacy] remove cli of benchmark and update optim

* [doc] fix cli doc test

* [legacy] fix engine clip grad norm

* [legacy] remove outdated colo tensor (#4694)

* [legacy] remove outdated colo tensor

* [test] fix test import

* [legacy] move outdated zero to legacy (#4696)

* [legacy] clean up utils (#4700)

* [legacy] clean up utils

* [example] update examples

* [legacy] clean up amp

* [legacy] fix amp module

* [legacy] clean up gpc (#4742)

* [legacy] clean up context

* [legacy] clean core, constants and global vars

* [legacy] refactor initialize

* [example] fix examples ci

* [example] fix examples ci

* [legacy] fix tests

* [example] fix gpt example

* [example] fix examples ci

* [devops] fix ci installation

* [example] fix examples ci

colossalai/legacy/zero/sharded_model/utils.py

@@ -0,0 +1,20 @@
+import copy
+
+import torch
+
+from colossalai.legacy.zero.sharded_model import ShardedModelV2
+
+
+def col_model_deepcopy(sharded_model: ShardedModelV2, other_model: torch.nn.Module):
+    """
+    copy param of the ShardedModelV2 to other_model.
+    Note the other_model has to be the same as self.
+    """
+    for zero_param, param in zip(sharded_model.parameters(), other_model.parameters()):
+        assert hasattr(zero_param, 'colo_attr')
+        shard_flag = zero_param.colo_attr.sharded_data_tensor.is_sharded
+        if shard_flag:
+            sharded_model.shard_strategy.gather([zero_param.colo_attr.sharded_data_tensor])
+        param.data = copy.deepcopy(zero_param.colo_attr.data_payload)
+        if shard_flag:
+            sharded_model.shard_strategy.shard([zero_param.colo_attr.sharded_data_tensor])