Update README.md

README.md

@@ -71,6 +71,7 @@ image_inputs = processor(
 # Get embeddings
 query_embedding = model.encode_query(query_inputs)
 doc_embedding = model.encode_passage(image_inputs)
+```
 
 ### Limitations and Future Work
 
@@ -108,7 +109,7 @@ deepspeed --include localhost:0 --master_port 60000 train.py \
   --query_max_len 128 \
   --passage_max_len 512 \
   --num_train_epochs 1
-  ```
+```
 
 ### License
 Same as base model HuggingFaceTB/SmolVLM-256M-Base