Access to pretrained model weights

Efficient-Large-Model / 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

878 stars 55 forks source link

Access to pretrained model weights #68

Open zzxslp opened 1 month ago

zzxslp commented 1 month ago

Hi, thanks for the great work!

May I know if we have access to non-instruct models? (e.g., models after stage-1 or stage-2). For my specific research use case, I would love to access the model weights after mm_align + pretrain (before SFT).

yaolug commented 4 weeks ago

We will release stage-2 model checkpoints soon.

zzxslp commented 4 weeks ago

Thanks, looking forward to it.

UelisonSantos commented 5 days ago

Hello, When will the model checkpoint be released? I am working on a paper and would love to include VILA in the tests. This would be a tremendous help for me!