So my fine-tuning file is somthing like this:
{"messages": [{"role": "user", "content": "All persons begin with tag <PER> and end with tag </PER>"}, {"role": "assistant", "content": "OK. I will identify person with tags <PER> and </PER>"}]}
{"messages": [{"role": "user", "content": "Extract person names enclosed within '<PER>' tag and '</PER>' For example Can you find person names? - <PER>teghwjw ugiqfhfv</PER> received a promotion at work for his outstanding performance.Yes, I can find person names within the provided text. In this case, the person's name appears to be <PER>teghwjw ugiqfhfv</PER>."}, {"role": "assistant", "content": "Yes, I can find person names within the provided text. In this case, the person's name appears to be <PER>teghwjw ugiqfhfv</PER>"}]}
where my data will be masked using some value random and enclosed in a XML tags depending upon the entity(if the data is person name a random value will replace the data enclosed in xml tag). I have instructed in the file indicating that for eg asdqeqwe123 is person name(for almost 10 different tags), and I have given a few examples for each tag.