# Which model to select

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhich-model-to-select%2F150315%3E%5C
**Category:** Models\
**Created:** [April 14, 2025, 8:04am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhich-model-to-select%2F150315 "2025-04-14T08:04:29Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Madhavkumar1998](https://avatars.discourse-cdn.com/v4/letter/m/4da419/32.png) [@Madhavkumar1998](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMadhavkumar1998)%5C
**Post date:** [April 14, 2025, 8:04am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhich-model-to-select%2F150315%2F1 "2025-04-14T08:04:29Z")

</div>

My task is to extract data from a document and make key value pair can any one suggest an open source light weight model ?

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [April 14, 2025, 8:32am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhich-model-to-select%2F150315%2F2 "2025-04-14T08:32:15Z")

</div>

If I assume that the document is an image, it would be around here.  
If it’s text information, I think Qwen 2.5 0.5B or SmoLLM would work.

> **[Accelerating Document AI](https://huggingface.co/blog/document-ai)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

> [@Improving Key-Value Pair Extraction with LayoutLM and LiLT on Custom OCR Dataset](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimproving-key-value-pair-extraction-with-layoutlm-and-lilt-on-custom-ocr-dataset%2F135483)%3A
>
> I am working on an OCR project to perform document understanding on a specific type of document with a fixed layout (e.g., mandate forms). The layout has minor variations across images. My goal is to accurately extract key-value pairs and output them in JSON format. What I Have Done Dataset Preparation: I created a dataset of 231 annotated images in FUNSD format using the UBIAI tool. The annotations include bounding boxes and labels (KEY, VALUE). Models Used: I fine-tuned both LayoutLMv3 …

> [@Which Model Should I Choose: TrOCR, TrOCR + LayoutLM, or Donut?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhich-model-should-i-choose-trocr-trocr-layoutlm-or-donut%2F145295)%3A
>
> I am developing a web application to process a collection of scanned domain-specific documents with five different types of documents, as well as one type of handwritten form. The form contains a mix of printed and handwritten text, while others are entirely printed but all of the other documents would contain the name of the person. Key Requirements: Search Functionality – Users should be able to search for a person’s name and retrieve all associated scanned documents. Key-Value Pair Extracti…