Update README.md

README.md

@@ -16,11 +16,9 @@ Kosmos-2.5 is a multimodal literate model for machine reading of text-intensive
 Since this is a generative model, there is a risk of **hallucination** during the generation process, and it **CAN NOT** guarantee the accuracy of all OCR/Markdown results in the images.
 
 ## Inference
-### Markdown Task
-For usage instructions, please refer to [md.py](md.py).
+**Markdown Task:** For usage instructions, please refer to [md.py](md.py).
 
-### OCR Task
-For usage instructions, please refer to [ocr.py](ocr.py).
+**OCR Task:** For usage instructions, please refer to [ocr.py](ocr.py).
 
 ## Citation