Update README.md

README.md

@@ -123,6 +123,21 @@ print(tokenizer.decode(outputs[0, input_length:], skip_special_tokens=True))
 Using this template, each turn is preceded by a `<|im_start|>` delimiter and the role of the entity 
 (either `user`, for content supplied by the user, or `assistant` for LLM responses), and finished with the `<|im_end|>` token.
 
+### Post-edition
+
+For post-edition tasks you can try using the following prompt template:
+
+```python
+source = 'Catalan'
+target = 'English'
+source_sentence = 'Necessite saber qui son Rafael Nadal i Maria Magdalena.'
+machine_translation = 'I need to know who is Rafael Christmas and Maria the Muffin.'
+
+text = f"Please fix any mistakes in the following {source}-{target} machine translation or keep it unedited if it's correct.\nSource: {source_sentence} \nMT: {machine_translation} \nCorrected:"
+
+# I need to know who is Rafael Nadal and Maria Magdalena.
+```
+
 
 ## Data