Feature Extraction
Transformers
PyTorch
vjepa2_fmri_encoder_enhanced
neuroscience
fmri
video
v-jepa
brain-alignment
custom_code
Instructions to use epfl-neuroai/vjepa2-encoder-enhanced with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use epfl-neuroai/vjepa2-encoder-enhanced with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="epfl-neuroai/vjepa2-encoder-enhanced", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("epfl-neuroai/vjepa2-encoder-enhanced", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download enhanced_bmd_to_mcmahon.pth from epfl-neuroai/vjepa2-encoder-enhanced: direct link, hf CLI and curl.
- Browser
- Download file 116 MB
-
https://huggingface.co/epfl-neuroai/vjepa2-encoder-enhanced/resolve/main/enhanced_bmd_to_mcmahon.pth
- Command line
-
hf download hf://epfl-neuroai/vjepa2-encoder-enhanced/enhanced_bmd_to_mcmahon.pth
-
curl -L -o enhanced_bmd_to_mcmahon.pth https://huggingface.co/epfl-neuroai/vjepa2-encoder-enhanced/resolve/main/enhanced_bmd_to_mcmahon.pth
116 MB
- Xet hash:
- 03ddfbd29469b0ac024ece0d08e242bb3579cd330fcdf26ae4ea18a9cd8ef8cc
- Size of remote file:
- 116 MB
- SHA256:
- 2b9c9e7f5effb8be0092697cfab076977323d2330577e8e1fdbeff87f5b3ce35
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.