Skip to content

ishani-ss/Visual-Language-Model-Backends

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 

Repository files navigation

Visual Language Model (VLM) Backends

Understanding the differences between virtual language model (vLLMs) and transformer backends for document parsing.

Business Use Case:

  • Models that read documents of varying lengths and types of documents (e.g. invoices, bank transactions, large text-based documents, image scans, tabular documents, etc.) are required.
  • Models that read these documents quickly and efficiently, even if documents are multi-page are essential.
  • Models that are easy to run and use by Data Scientists are essential.

Research Question:

  • Are document parsing visual language models that use a vLLM backend better suited to the Business Use Case than models that use a transformer backend?

Research Findings:

About

This repository contains research and experimentation on the backend engines of document parsing visual language models.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors