Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
vidore
's Collections
ColPali Models
ColQwen2 Models
ColSmolVLM
Hf-native ColVision Models
ViDoRe Benchmark
ViDoRe Benchmark (BEIR)
ViDoRe Chunk OCR (baseline)
ColPali Paper Resources
ViDoRe Page OCR (artifact)
ColSmolVLM
updated
4 days ago
Pre-trained checkpoints for the ColVision models with a ColSmolVLM backbone.
Upvote
1
vidore/colSmol-500M
Updated
4 days ago
•
211
•
8
vidore/colSmol-256M
Updated
4 days ago
•
334
•
5
Upvote
1
Share collection
View history
Collection guide
Browse collections