Image Feature Extraction
Transformers
Safetensors
pixtral_large4_vision
feature-extraction
vision
custom_code
Instructions to use immanuelpeter/PixtralViT-Large-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use immanuelpeter/PixtralViT-Large-4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="immanuelpeter/PixtralViT-Large-4", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("immanuelpeter/PixtralViT-Large-4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
Today
-
Restore the approved card
Verified signature6e7365d -
Synchronize maintained vision bundle layout and manifest
Verified signature9a8982a -
Synchronize maintained vision bundle layout and manifest
Verified signature4d83a56 -
Synchronize maintained vision bundle layout and manifest
Verified signaturedb58047 -
Drop .gitattributes from the manifest
Verified signature0fba443 -
Drop the AutoModel sentence from the card
Verified signaturebb7647c -
Slim the card to the previous releases' form
Verified signature12606c9 -
Complete the concise card inventory and usage
Verified signature027d0da -
Reconcile the house-template card; file SHA256 in the manifest; weights unchanged (vision-tower-bench 85b65d0)
Verified signature0605fc9 -
Rewrite the card in the house template
Verified signatured5c6ce3 -
House-template card, fixed 448 px example, normalized manifest with file SHA256; weights unchanged
Verified signature0f0835a
Yesterday
-
Ship the parent-order forward (modeling_pixtral_large4.py) and correct the card; weights unchanged (vision-tower-bench 5139e1a)
Verified signature3cd67e8 -
Add the Mistral Large 4 Pixtral Tower and Projector
Verified signature204c1fe -
initial commit
Verified signature0cbdd67