# Paraphrasing for style

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fparaphrasing-for-style%2F55369%3E%5C
**Category:** Models\
**Created:** [September 18, 2023, 2:22am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fparaphrasing-for-style%2F55369 "2023-09-18T02:22:38Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![yeshwanthv5](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/yeshwanthv5/32/18621_2.png) [@yeshwanthv5](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fyeshwanthv5)%5C
**Post date:** [September 18, 2023, 2:22am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fparaphrasing-for-style%2F55369%2F1 "2023-09-18T02:22:38Z")

</div>

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.