Add code highlighting and "image-text-to-text" tag

README.md

@@ -7,6 +7,7 @@ tags:
   - multimodal
   - midi
   - phi-3
+  - image-text-to-text
   - question-answering
   - optical-music-recognition
 model-index:
@@ -25,7 +26,8 @@ This adapter equips Phi-3 with the ability to perform symbolic music reasoning a
 ---
 
 ## Inference
-```
+
+```python
 from transformers import AutoModelForCausalLM 
 from transformers import AutoProcessor