Update README.md

README.md

@@ -51,30 +51,9 @@ We introduce MathCoder-VL, a series of open-source large multimodal models (LMMs
 
 
 ## Usage
-For training and inference code, please refer to [InternVL](https://github.com/OpenGVLab/InternVL).
+For training and inference code, please refer to [InternVL2-8B](https://huggingface.co/OpenGVLab/InternVL2-8B).
 
-```
-from datasets import load_dataset
-from PIL import Image
-from io import BytesIO
-
-mm_mathinstruct = load_dataset("MathLLMs/MM-MathInstruct")
-print(mm_mathinstruct)
-
-# show the last image
-img = Image.open(BytesIO(mm_mathinstruct['train'][-1]['image']))
-img.show()
-```
 
-It should print:
-```
-DatasetDict({
-    train: Dataset({
-        features: ['id', 'image', 'question', 'solution', 'image_path'],
-        num_rows: 2871988
-    })
-})
-```
 
 ### Prompt for TikZ Code Generation
 
@@ -109,17 +88,7 @@ Please provide the Python code needed to reproduce this image.\n<image>
   <img src="./examples/fig2.png" width="100%" title="Result Figure">
 </div>
 
-## Construction of MathCoder-VL
 
-<div align="center">
-  <img src="./examples/fig4.png" width="100%" title="Result Figure">
-</div>
-
-## Performance
-
-<div align="center">
-  <img src="./examples/tab1.png" width="100%" title="Result Figure">
-</div>
 
 ## **Citation**