Downloads · 30 days
0
htmlsift-release
koivualeksi/htmlsift-release
htmlsift-release is a machine learning model from koivualeksi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Weights for htmlsift, a web main-content extractor (HTML in, clean text / HTML / markdown out).
Access
Public
Updated Sep 23, 2026
Repo size
2.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1 GB · 79%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Sep 16, 2026
- Updated
- Sep 23, 2026
- SHA
- d65d207e
Base models
Model card
From the Hugging Face model README
htmlsift model weights
Weights for htmlsift, a web main-content extractor (HTML in, clean text / HTML / markdown out).
mini/— int8 ONNX bundle, runs on CPU.pip install htmlsiftbase/— 311M encoder bundle (Granite r2, first 10 layers), GPU-capable.pip install htmlsift[full]
The weights are fetched automatically on first use — you don't download them by hand.
License and attribution
Weights are licensed Apache-2.0. They are trained on WebMainBench (Apache-2.0) — please attribute WebMainBench when you use them.
- License
- apache-2.0
- Created
- Sep 16, 2026
- Updated
- Sep 23, 2026