how to finetune? - Githubissues

NVlabs / VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

Apache License 2.0

1.73k stars 134 forks source link

Closed lxw919 closed 3 weeks ago

lxw919 commented 1 month ago

If I want to use M3IT(or others) dataset to finetune the model,how I setup? data_mixture?

Lyken17 commented 1 month ago

you need to download data follow data_prepare and register the following entries in data_mixture.