artidoro / qlora

QLoRA: Efficient Finetuning of Quantized LLMs
https://arxiv.org/abs/2305.14314
MIT License
10.06k stars 822 forks source link

Using QLORA for Multi Modal Vison Foundation Models Optimization - google/owlv2-base-patch16-ensemble #281

Open solomonmanuelraj opened 11 months ago

solomonmanuelraj commented 11 months ago

Hi Team,

I am working in OWL-VIT v2 model ( google/owlv2-base-patch16-ensemble - https://huggingface.co/google/owlv2-base-patch16-ensemble/tree/main) for object detection. I want to optimize the model and reduce the memory size so that i can deploy in the edge device.

Do you have any use cases / references for this Multi Modal Vision Foundation model optimization using QLORA?

your reference / comments will be very helpful.