diff --git a/distributed/tensor_parallelism/README.md b/distributed/tensor_parallelism/README.md
index ec61071e65..a3c36e3864 100644
--- a/distributed/tensor_parallelism/README.md
+++ b/distributed/tensor_parallelism/README.md
@@ -10,7 +10,25 @@ PyTorch native Tensor Parallel APIs, which include:
 More details about the PyTorch native Tensor Parallel APIs, please see PyTorch docs:
 https://pytorch.org/docs/stable/distributed.tensor.parallel.html
 
-```
+## Installation
+
+```bash
 pip install -r requirements.txt
-torchrun --nnodes 1 --nproc-per-node 4 tensor_parallel_example.py
 ```
+
+## Running Examples
+
+You can run the examples using `torchrun` to launch distributed training:
+
+```bash
+# Simple Tensor Parallel example
+torchrun --nnodes=1 --nproc_per_node=4 tensor_parallel_example.py
+
+# Tensor Parallel with Sequence Parallel
+torchrun --nnodes=1 --nproc_per_node=4 sequence_parallel_example.py
+
+# FSDP + Tensor Parallel with Llama2 model
+torchrun --nnodes=1 --nproc_per_node=4 fsdp_tp_example.py
+```
+
+For more details, check the `run_examples.sh` script.
diff --git a/distributed/tensor_parallelism/fsdp_tp_example.py b/distributed/tensor_parallelism/fsdp_tp_example.py
index 87935f10f0..4ae6cb1aa2 100644
--- a/distributed/tensor_parallelism/fsdp_tp_example.py
+++ b/distributed/tensor_parallelism/fsdp_tp_example.py
@@ -1,34 +1,3 @@
-import sys
-import os
-import torch
-import torch.distributed as dist
-import torch.nn as nn
-import torch.nn.functional as F
-
-from log_utils import rank_log, get_logger, verify_min_gpu_count
-
-# ---- GPU check ------------
-_min_gpu_count = 4
-
-if not verify_min_gpu_count(min_gpus=_min_gpu_count):
-    print(f"Unable to locate sufficient {_min_gpu_count} gpus to run this example. Exiting.")
-    sys.exit()
-# ---------------------------
-
-from llama2_model import Transformer, ModelArgs
-
-from torch.distributed.device_mesh import init_device_mesh
-from torch.distributed.fsdp import FullyShardedDataParallel as FSDP
-from torch.distributed._tensor import Shard, Replicate
-from torch.distributed.tensor.parallel import (
-    parallelize_module,
-    ColwiseParallel,
-    RowwiseParallel,
-    PrepareModuleInput,
-    SequenceParallel
-)
-
-
 """
 This is the script to test 2D Parallel which combines Tensor/Sequence
 parallel with Fully Sharded Data Parallel (TP/SP + FSDP) on a example
@@ -60,6 +29,36 @@
 https://pytorch.org/tutorials/intermediate/TP_tutorial.html
 """
 
+import sys
+import os
+import torch
+import torch.distributed as dist
+import torch.nn as nn
+import torch.nn.functional as F
+
+from log_utils import rank_log, get_logger, verify_min_gpu_count
+
+# ---- GPU check ------------
+_min_gpu_count = 4
+
+if not verify_min_gpu_count(min_gpus=_min_gpu_count):
+    print(f"Unable to locate sufficient {_min_gpu_count} gpus to run this example. Exiting.")
+    sys.exit()
+# ---------------------------
+
+from llama2_model import Transformer, ModelArgs
+
+from torch.distributed.device_mesh import init_device_mesh
+from torch.distributed.fsdp import FullyShardedDataParallel as FSDP
+from torch.distributed._tensor import Shard, Replicate
+from torch.distributed.tensor.parallel import (
+    parallelize_module,
+    ColwiseParallel,
+    RowwiseParallel,
+    PrepareModuleInput,
+    SequenceParallel
+)
+
 tp_size = 2
 logger = get_logger()
 
diff --git a/distributed/tensor_parallelism/sequence_parallel_example.py b/distributed/tensor_parallelism/sequence_parallel_example.py
index b145fbc95e..988973af4b 100644
--- a/distributed/tensor_parallelism/sequence_parallel_example.py
+++ b/distributed/tensor_parallelism/sequence_parallel_example.py
@@ -1,5 +1,22 @@
-# The following is an example command to run this code
-# torchrun --nnodes 1 --nproc-per-node 4 sequence_parallel_example.py
+"""
+This is the script to test Sequence Parallel(SP) on a toy model in a
+Megetron-LM SPMD style. We show an E2E working flow from forward,
+backward and optimization.
+
+We use the example of two `nn.Linear` layers with an element-wise `nn.RELU`
+in between to show an example of sequence parallel, which was proposed in paper:
+
+https://arxiv.org/pdf/2205.05198.pdf.
+
+Like tensor parallel, we parallelize the first linear layer by column
+and also parallelize the second linear layer by row. But the input in each rank
+now is different so that we need one all-gather for input and one reduce-scatter
+in the end of the second linear layer.
+
+The following is an example command to run this code
+    torchrun --nnodes 1 --nproc-per-node 4 sequence_parallel_example.py
+"""
+
 import os
 import sys
 import torch
@@ -24,28 +41,8 @@
     sys.exit()
 # ---------------------------
 
-
 from torch.distributed._tensor.device_mesh import init_device_mesh
 
-
-
-"""
-This is the script to test Sequence Parallel(SP) on a toy model in a
-Megetron-LM SPMD style. We show an E2E working flow from forward,
-backward and optimization.
-
-We use the example of two `nn.Linear` layers with an element-wise `nn.RELU`
-in between to show an example of sequence parallel, which was proposed in paper:
-
-https://arxiv.org/pdf/2205.05198.pdf.
-
-Like tensor parallel, we parallelize the first linear layer by column
-and also parallelize the second linear layer by row. But the input in each rank
-now is different so that we need one all-gather for input and one reduce-scatter
-in the end of the second linear layer.
-"""
-
-
 class ToyModel(nn.Module):
     """MLP based model"""
 
diff --git a/distributed/tensor_parallelism/tensor_parallel_example.py b/distributed/tensor_parallelism/tensor_parallel_example.py
index b96f982f0c..c42a952ea8 100755
--- a/distributed/tensor_parallelism/tensor_parallel_example.py
+++ b/distributed/tensor_parallelism/tensor_parallel_example.py
@@ -1,31 +1,3 @@
-# The following is an example command to run this code
-# torchrun --nnodes 1 --nproc-per-node 4 tensor_parallel_example.py
-import os
-import sys
-import torch
-import torch.nn as nn
-
-from torch.distributed.tensor.parallel import (
-    parallelize_module,
-    ColwiseParallel,
-    RowwiseParallel,
-)
-
-from log_utils import rank_log, get_logger, verify_min_gpu_count
-
-# ---- GPU check ------------
-_min_gpu_count = 2
-
-if not verify_min_gpu_count(min_gpus=_min_gpu_count):
-    print(f"Unable to locate sufficient {_min_gpu_count} gpus to run this example. Exiting.")
-    sys.exit()
-# ---------------------------
-
-from torch.distributed._tensor.device_mesh import init_device_mesh
-
-
-
-
 """
 This is the script to test Tensor Parallel(TP) on a toy model in a
 Megetron-LM SPMD style. We show an E2E working flow from forward,
@@ -55,8 +27,33 @@
 to use and our `parallelize_module` API will parse and parallelize the modules
 based on the given `ParallelStyle`. We are using this PyTorch native Tensor
 Parallelism APIs in this example to show users how to use them.
+
+The following is an example command to run this code
+    torchrun --nnodes 1 --nproc-per-node 4 tensor_parallel_example.py
 """
 
+import os
+import sys
+import torch
+import torch.nn as nn
+import torch.distributed as dist
+from torch.distributed.tensor.parallel import (
+    parallelize_module,
+    ColwiseParallel,
+    RowwiseParallel,
+)
+from log_utils import rank_log, get_logger, verify_min_gpu_count
+
+# ---- GPU check ------------
+_min_gpu_count = 2
+
+if not verify_min_gpu_count(min_gpus=_min_gpu_count):
+    print(f"Unable to locate sufficient {_min_gpu_count} gpus to run this example. Exiting.")
+    sys.exit()
+# ---------------------------
+
+from torch.distributed._tensor.device_mesh import init_device_mesh
+
 class ToyModel(nn.Module):
     """MLP based model"""