Update README.md

README.md

@@ -138,6 +138,8 @@ For improved practical inference speed, we strongly recommend running Jellyfish
 We provide two simple Python code examples for inference using the Jellyfish model.  
 
 #### Using Transformers and Torch Modules
+<div style="height: auto; max-height: 400px; overflow-y: scroll;">
+  
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 import torch
@@ -192,6 +194,7 @@ response = tokenizer.decode(
 print(response)
 
 ```
+</div>
 
 #### Using vLLM
 ```python