Spaces:

feyninc
/

pulpie

Running on Zero

App Files Files Community

pulpie / README.md

bhavnicksm

Pin gradio SDK 6.17.3: 6.18+ forces hub 1.x, incompatible with transformers

74cf5ff 13 days ago

preview code

Raw

History Blame Contribute Delete

989 Bytes

A newer version of the Gradio SDK is available: 6.20.0

Upgrade

metadata

title: Pulpie
emoji: 🍊
colorFrom: red
colorTo: yellow
sdk: gradio
sdk_version: 6.17.3
python_version: '3.13'
app_file: app.py
pinned: false
license: apache-2.0
short_description: Clean HTML 20x faster — encoder vs decoder, live
models:
  - feyninc/pulpie-orange-small
  - opendatalab/MinerU-HTML-v1.1-hunyuan0.5B-compact

Pulpie — encoder vs decoder

Extract the main content from any web page, side by side: pulpie (orange-small, 210M encoder) races Dripper (MinerU-HTML, 0.6B decoder) on the same page. Pulpie labels every block in a single forward pass; the decoder emits its answer one token at a time. Same quality (~0.86 ROUGE-5 F1 on WebMainBench), ~20x the speed.

pip install pulpie
Code: https://github.com/feyninc/pulpie
Benchmarks: https://github.com/feyninc/pulpie/blob/main/BENCHMARKS.md
Blog: https://usefeyn.com/blog/pulpie-pareto-optimal-models-for-cleaning-the-web/

Built by Feyn.