Image Feature Extraction
Transformers
Safetensors
levjepa
feature-extraction
video
self-supervised
jepa
vision-transformer
custom_code
Instructions to use galilai-group/LeVJEPA-VideoMix-Large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use galilai-group/LeVJEPA-VideoMix-Large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="galilai-group/LeVJEPA-VideoMix-Large", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("galilai-group/LeVJEPA-VideoMix-Large", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Hello fellow JEPA enthusiasts, i need some help.
#1
by mgstull2003 - opened
So I am doing research into LEV-Jepa usage for pick and place on a robot that specifically uses RGB-d, is there a version of this model available with RGBD pre-training?
hey, we currently have no plans for an RGB-d pretrained LeVJEPA. You should be able to finetune/continue pretraining the existing checkpoint with depth
Thanks for the update, ill give it a try and see how it comes out.
mgstull2003 changed discussion status to closed