Update README.md

README.md

@@ -35,6 +35,21 @@ The project is still in the testing phase, and the training parameters will cont
 - learning_rate=5e-5
 - max_grad_norm=1.0
 
+## Testing The Model
+
+Below, we have several examples of question-answer pairs comparing the pure Llama3 model with the Llama3 model fine tunned for the Galician language.
+
+*Llama3-8B*
+```bash
+User: Cal é a capital de Canadá?
+Assistant: Não! Cal não é a capital de Canadá. A capital de Canadá é Ottawa.
+```
+*Llama3-8B-Galician-Chat*
+```bash
+User: Cal é a capital de Canadá?
+Assistant: A capital de Canadá é Ottawa.
+```
+
 ## How to Use the Model
 
 To use this model, follow the example code provided below. Ensure you have the necessary libraries installed (e.g., Hugging Face's `transformers`).
@@ -48,7 +63,7 @@ pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
 pip install llmtuner
 ```
 
-### Test the model
+### Run the model
 
 ```bash
 from llmtuner import ChatModel