correct readme for image bbox output format

README.md

@@ -69,7 +69,7 @@ LightOnOCR-2 is an efficient end-to-end 1B-parameter vision-language model for c
 The output format for embedded images is:
 
 ```
-![image](image_N.png) x1,y1,x2,y2
+![image](image_N.png)x1,y1,x2,y2
 ```
 
 Where coordinates are normalized to `[0, 1000]`.
@@ -122,7 +122,7 @@ output_ids = model.generate(**inputs, max_new_tokens=1024)
 generated_ids = output_ids[0, inputs["input_ids"].shape[1]:]
 output_text = processor.decode(generated_ids, skip_special_tokens=True)
 print(output_text)
-# Output will include bounding boxes like: ![image](image_1.png) 120,50,850,400
+# Output will include bounding boxes like this(no space): ![image](image_1.png)120,50,850,400
 ```
 
 ---