Update README.md

README.md

@@ -33,14 +33,14 @@ More evaluations are ongoing.
 
 ## Model Preparations
 
-### Transformers Version
+#### - Transformers Version
 Make sure to have `transformers >= 4.35.3`.
 
-### Prompt Template
+#### - Prompt Template
 The model supports multi-image and multi-prompt generation. When using the model, make sure to follow the correct prompt template (`USER: <image>xxx\nASSISTANT:`), where `<image>` token is a place-holding special token for image embeddings.
 
 ## Model Inference from `pipeline` and `transformers`
-### Using `pipeline`:
+#### - Using `pipeline`:
 Below we used [`"bczhou/tiny-llava-v1-hf"`](https://huggingface.co/bczhou/tiny-llava-v1-hf) checkpoint.
 
 ```python
@@ -57,7 +57,7 @@ print(outputs[0])
 >>> {"generated_text': 'USER:  \nWhat does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud\nASSISTANT: The label 15 represents lava, which is a type of volcanic rock."}
 ```
 
-### Using pure `transformers`:
+#### - Using pure `transformers`:
 Below is an example script to run generation in `float16` precision on a GPU device:
 
 ```python