Update README.md

README.md

@@ -58,13 +58,13 @@ This MLX release converts the upstream checkpoint with **3-bit** quantization fo
 ## 🚀 Quickstart (CLI)
 
 **Single image caption**
-```bash
+```python
 python -m mlx_vlm.generate \
   --model <this-repo-id> \
   --image /path/to/image.jpg \
   --prompt "Describe this image in two concise sentences." \
   --max-tokens 128 --temperature 0.0 --device mps --seed 0
-
+```
 
 ## 🔀 Model Family Comparison (2-bit → 6-bit)