Update README.md

README.md

@@ -73,6 +73,10 @@ print(answer)
 
 # Inference
 
+## Online
+
+Currently, the HuggingFace's Inference Tool UI doesn't properly load the model. However, you can use it with regular Python code as shown above once you meet the [requirements](#requirements).
+
 ## CPU
 
 CPU inference is available via [GGML model](https://huggingface.co/danderian/zenos-gpt-j-6B-alpaca-evol-4bit/resolve/main/ggml-f16-q4_0.bin)
@@ -82,10 +86,6 @@ CPU inference is available via [GGML model](https://huggingface.co/danderian/zen
 - 4 cores
 - 4GB RAM
 
-## Online
-
-Currently, the HuggingFace's Inference Tool UI doesn't properly load the model. However, you can use it with regular Python code as shown above once you meet the [requirements](#requirements).
-
 # Acknowledgments
 
 This model was developed by [Nicolás Iglesias](mailto:[email protected]) using the Hugging Face Transformers library.