Update README.md

README.md

@@ -29,8 +29,7 @@ LLaVA-InternLM-7B | 69.0 | 68.5 | 66.7 | 63.8 | 37.3
 LLaVA-InternLM2-7B | 73.3 | 74.6 | 71.7 | 72.0 | 42.5
 llava-dinov2-internlm2-7b-v1 | 64.0 | 65.2 | 62.9 | 61.6 | 45.3
 
-## Quickstart
-### Installation
+## Installation
 ```
 git clone https://github.com/InternLM/xtuner
 pip install -e ./xtuner[deepspeed]
@@ -46,6 +45,7 @@ xtuner chat internlm/internlm2-chat-7b \
 --prompt-template internlm2_chat \
 --image $IMAGE_PATH
 ```
+
 ## Common Errors
 1. 
 ```
@@ -80,7 +80,7 @@ pip install protobuf
 
 ## Data prepration
 
-#### File structure
+1. File structure
 
 ```
 ./data/llava_data
@@ -104,7 +104,7 @@ pip install protobuf
         └── VG_100K_2
 ```
 
-#### Pretrain Data
+2. Pretrain Data
 
 LLaVA-Pretrain
 
@@ -114,11 +114,11 @@ git lfs install
 git clone https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain --depth=1
 ```
 
-#### Finetune Data
+3. Finetune Data
 
-1. Text data
+3.1 Text data
 
-   1. LLaVA-Instruct-150K
+    LLaVA-Instruct-150K
 
       ```shell
       # Make sure you have git-lfs installed (https://git-lfs.com)
@@ -126,15 +126,15 @@ git clone https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain --depth=1
       git clone https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K --depth=1
       ```
 
-2. Image data
+3.2 Image data
 
-   1. COCO (coco): [train2017](http://images.cocodataset.org/zips/train2017.zip)
+   3.2.1 COCO (coco): [train2017](http://images.cocodataset.org/zips/train2017.zip)
 
-   2. GQA (gqa): [images](https://downloads.cs.stanford.edu/nlp/data/gqa/images.zip)
+   3.2.2 GQA (gqa): [images](https://downloads.cs.stanford.edu/nlp/data/gqa/images.zip)
 
-   3. OCR-VQA (ocr_vqa): [download script](https://drive.google.com/drive/folders/1_GYPY5UkUy7HIcR0zq3ZCFgeZN7BAfm_?usp=sharing)
+   3.2.3 OCR-VQA (ocr_vqa): [download script](https://drive.google.com/drive/folders/1_GYPY5UkUy7HIcR0zq3ZCFgeZN7BAfm_?usp=sharing)
 
-      1. ⚠️ Modify the name of OCR-VQA's images to keep the extension as `.jpg`!
+      ⚠️⚠️⚠️ Modify the name of OCR-VQA's images to keep the extension as `.jpg`!
 
          ```shell
          #!/bin/bash
@@ -149,12 +149,11 @@ git clone https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain --depth=1
          done
          ```
 
-   4. TextVQA (textvqa): [train_val_images](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip)
+   3.2.4 TextVQA (textvqa): [train_val_images](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip)
 
-   5. VisualGenome (VG): [part1](https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip), [part2](https://cs.stanford.edu/people/rak248/VG_100K_2/images2.zip)
+   3.2.5 VisualGenome (VG): [part1](https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip), [part2](https://cs.stanford.edu/people/rak248/VG_100K_2/images2.zip)
 
-## Cheers! Train your model
- 
+## Cheers! Now train your own model!
 1. Alignment module pretraining
 ```
 NPROC_PER_NODE=8 xtuner train ./llava_internlm2_chat_7b_dinov2_e1_gpu8_pretrain.py --deepspeed deepspeed_zero2