HNGlance

Top Best New Show

Fine-Tuning VLMs for Data Extraction

https://nanonets.com/blog/fine-tuning-vision-language-models-vlms-for-data-extraction/

by OceanBreez • 2 years ago

6 2 2 years ago

NA

Related Stories

Loading related stories...

Comments

2

cvaman• 2 years ago

Is it possible to host multiple fine-tuned VLMs on a single machine? like multiple models sharing the GPU(s) for inference?

spikyspider• 2 years ago

Yeah. If you have a large enough GPU you can use vanilla pytorch to load as many models as required. Docker is a good option if you have isolated services. Triton, TensorRT, TorchServe, RAY are also good services to checkout, especially when you want to load multiple adapters for the same LLM/VLM backbone. Is there anything specific you are looking to serve?

Source preview

nanonets.com

HNGlance

© 2024-2026 HN Glance. Story content belongs to its original sources.

Privacy
Terms