Update README.md

README.md

@@ -20,3 +20,14 @@ base_model: unsloth/llama-3-8b-bnb-4bit
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+# Generation format
+```
+<|translate|>
+<|eng|>
+Hello world
+<|jap|>
+ハロー・ワールド
+<|ind|>
+Halo dunia
+```