Is there any model fine-tuned for paraphrasing text into a given style?
Example: “Rephrase the following text in Shakespeare’s style. Text: …”
I tried using the mainstream models from openllm leaderboard but the outputs are inconsistent. Any suggestions are welcome.
Edit: More specifically I tried the llama-2 7b and 13b models. They seem to work when the prompt was short but fail when provided with a longer sequence.