[hotfix]fix argument naming in docs and examples (#4083)

docs/source/en/advanced_tutorials/parallelize_your_training_like_Megatron.md

@@ -181,7 +181,7 @@ def gemini_zero_dpp(model: torch.nn.Module, pg: ProcessGroup, placement_policy:
                         device=get_current_device(),
                         placement_policy=placement_policy,
                         pin_memory=True,
-                        search_range_mb=32)
+                        search_range_m=32)
     return model
 ```
 
@@ -190,3 +190,5 @@ def gemini_zero_dpp(model: torch.nn.Module, pg: ProcessGroup, placement_policy:
 The above optimization we made allows us to pretrain the GPT-2 model on a single GPU. We only need to set the parameter `GPUNUM`=1 in `run.sh`, and then we can complete the model training on a single GPU when running the file.
 
 The GPT-2 example is accessible at [Train GPT with Colossal-AI](https://github.com/hpcaitech/ColossalAI/tree/main/examples/language/gpt).
+
+<!-- doc-test-command: torchrun --standalone --nproc_per_node=1 parallelize_your_training_like_Megatron.py  -->

docs/source/en/features/zero_with_chunk.md

@@ -67,12 +67,12 @@ Define the model parameters as follows:
 chunk_manager = init_chunk_manager(model=module,
                                            init_device=device,
                                            hidden_dim=hidden_dim,
-                                           search_range_mb=search_range_mb,
-                                           min_chunk_size_mb=min_chunk_size_mb)
+                                           search_range_m=search_range_m,
+                                           min_chunk_size_m=min_chunk_size_m)
 gemini_manager = GeminiManager(placement_policy, chunk_manager)
 ```
 
-`hidden_dim` is the hidden dimension of DNN. Users can provide this argument to speed up searching. If users do not know this argument before training, it is ok. We will use a default value 1024. `min_chunk_size_mb` is the the minimum chunk size in MegaByte. If the aggregate size of parameters is still smaller than the minimum chunk size, all parameters will be compacted into one small chunk.
+`hidden_dim` is the hidden dimension of DNN. Users can provide this argument to speed up searching. If users do not know this argument before training, it is ok. We will use a default value 1024. `min_chunk_size_m` is a floating point, being the minimum chunk size divided by 2^20 (e.g., if min_chunk_size_m=2.5, then the minimum chunk size should be 2.5*(2^20)).If the aggregate size of parameters is still smaller than the minimum chunk size, all parameters will be compacted into one small chunk.
 
 Initialization of the optimizer.
 ```python

docs/source/zh-Hans/advanced_tutorials/parallelize_your_training_like_Megatron.md

@@ -165,7 +165,7 @@ def gemini_zero_dpp(model: torch.nn.Module, pg: ProcessGroup, placement_policy:
                         device=get_current_device(),
                         placement_policy=placement_policy,
                         pin_memory=True,
-                        search_range_mb=32)
+                        search_range_m=32)
     return model
 ```
 
@@ -174,3 +174,6 @@ def gemini_zero_dpp(model: torch.nn.Module, pg: ProcessGroup, placement_policy:
 我们做的上述优化让我们可以在单GPU上训练GPT-2模型，只需要将`run.sh`中设置参数`GPUNUM`=1，再运行文件时就可以在单个GPU上完成模型的训练。
 
 GPT-2 示例在[Train GPT with Colossal-AI](https://github.com/hpcaitech/ColossalAI/tree/main/examples/language/gpt). 获得。
+
+
+<!-- doc-test-command: torchrun --standalone --nproc_per_node=1 parallelize_your_training_like_Megatron.py  -->

docs/source/zh-Hans/features/zero_with_chunk.md

@@ -66,13 +66,13 @@ with ColoInitContext(device='cpu', default_dist_spec=default_dist_spec, default_
 chunk_manager = init_chunk_manager(model=module,
                                    init_device=device,
                                    hidden_dim=hidden_dim,
-                                   search_range_mb=search_range_mb,
-                                   min_chunk_size_mb=min_chunk_size_mb)
+                                   search_range_m=search_range_m,
+                                   min_chunk_size_m=min_chunk_size_m)
 gemini_manager = GeminiManager(placement_policy, chunk_manager)
 model = ZeroDDP(model, gemini_manager)
 ```
 
-`hidden dim`是DNN的隐藏维度。用户可以提供这个参数来加快搜索速度。如果用户在训练前不知道这个参数也可以。 我们将使用默认值 1024。`min_chunk_size_mb`是以兆字节为单位的最小块大小。如果参数的总大小仍然小于最小块大小，则所有参数将被压缩为一个小块。
+`hidden dim`是DNN的隐藏维度。用户可以提供这个参数来加快搜索速度。如果用户在训练前不知道这个参数也可以。 我们将使用默认值 1024。`min_chunk_size_m`是以兆（2^20）为单位的最小块大小。如果参数的总大小仍然小于最小块大小，则所有参数将被压缩为一个小块。
 
 初始化优化器。
 ```python