# Fine-tune LLM model for document analysis

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tune-llm-model-for-document-analysis%2F107142%3E%5C
**Category:** Models\
**Created:** [September 18, 2024, 3:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tune-llm-model-for-document-analysis%2F107142 "2024-09-18T03:49:00Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Jermaine1996](https://avatars.discourse-cdn.com/v4/letter/j/cdc98d/32.png) [@Jermaine1996](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJermaine1996)%5C
**Post date:** [September 18, 2024, 3:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tune-llm-model-for-document-analysis%2F107142%2F1 "2024-09-18T03:49:00Z")

</div>

We have built a project about document data extraction by fine-tune LayoutLM series model. The processs is like first using OCR engine to get the words and bboxs. Then fine-tuned model will predict the entity type and build the relationship between these entities.

Now we are searching if there has a multi-modal LLM can be fine-tuned by our specific source documents?