nit: resolves format issues

Author: zhangch9

docs/04-Finetune/02-Quick Start.md

@@ -27,15 +27,16 @@ We recommend that you read the corresponding [model card](../05-Model%20Card.mdx
 :::
 
 1. Navigate to the `CogKit/` directory after cloning the repository
+
    ```bash
    cd CogKit/
    ```
 
-2. Choose the appropriate sub directory from the `quickstart/scripts` based on your task type and distribution strategy. For example, `t2i` corresponds to text-to-image task
+2. Choose the appropriate subdirectory from the `quickstart/scripts` based on your task type and distribution strategy. For example, `t2i` corresponds to text-to-image task
 
 3. Review and adjust the parameters in `config.yaml` in the selected training directory
 
-4. Run the script in selected directory:
+4. Run the script in the selected directory:
 
    ```bash
    bash start_train.sh
@@ -45,7 +46,9 @@ We recommend that you read the corresponding [model card](../05-Model%20Card.mdx
 
 ### Merge Checkpoint
 
-After fine-tuning, you need to use the `merge.py` script provided in the `quickstart/tools/converters` directory to merge the distributed checkpoint weights into a single checkpoint (**except for QLoRA fine-tuning**). For example:
+After fine-tuning, you need to use the `merge.py` script to merge the distributed checkpoint weights into a single checkpoint (**except for QLoRA fine-tuning**).
+The script can be found in the `quickstart/tools/converters` directory.
+For example:
 
 ```bash
 cd quickstart/tools/converters

tools/converters/merge.py

@@ -1,12 +1,15 @@
-#! /usr/bin/env python
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
 
 import argparse
+from pathlib import Path
 
 import torch
+from safetensors.torch import save_file
 from torch.distributed.checkpoint.format_utils import dcp_to_torch_save
-from pathlib import Path
+
 from cogkit.utils.lora import _LORA_WEIGHT_NAME
-from safetensors.torch import save_file
 
 TORCH_SAVE_CHECKPOINT_DIR = "diffusion_pytorch_model.bin"