# MEMORY FINETUNNING: Data preparation for Chat. I only have long chunks of proprietary text data

**URL:** <https://community.deeplearning.ai/t/memory-finetunning-data-preparation-for-chat-i-only-have-long-chunks-of-proprietary-text-data/678803>\
**Category:** Improving Accuracy of LLM Applications\
**Created:** [August 16, 2024, 3:52pm UTC](https://community.deeplearning.ai/t/memory-finetunning-data-preparation-for-chat-i-only-have-long-chunks-of-proprietary-text-data/678803 "2024-08-16T15:52:42Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ggustavo](https://avatars.discourse-cdn.com/v4/letter/g/ee59a6/32.png) [@ggustavo](https://community.deeplearning.ai/u/ggustavo)\
**Post date:** [August 16, 2024, 3:52pm UTC](https://community.deeplearning.ai/t/memory-finetunning-data-preparation-for-chat-i-only-have-long-chunks-of-proprietary-text-data/678803/1 "2024-08-16T15:52:42Z")

</div>

I’m planning to do memory fine-tune on an instruction-based model to replace a RAG and utilize proprietary data.

The language model will primarily serve for chat purposes and other instructional tasks. I have long chunks of proprietary text data. No pairs of QA. How should I proceed with the finetunning? Should I fine tune in text complition?

Any guidance or tips would be greatly appreciated!