Feature Extraction
Transformers
English
torch
clip
vision
interpretability
sparse autoencoder
sae
mechanistic interpretability
Instructions to use Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-9-hook_resid_post-l1-8e-05 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-9-hook_resid_post-l1-8e-05 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-9-hook_resid_post-l1-8e-05")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-9-hook_resid_post-l1-8e-05", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- cd692ea0de5132c433e6fc8f669a633d479ceffbbdd75c809a18950594b0b93f
- Size of remote file:
- 302 MB
- SHA256:
- b30062c7f724a65c6d1e7782e1c18f9e8b26a4dccbf2edd3fa90b509ef1b44aa
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.