HPD-Parsing

PaddlePaddle/HPD-Parsing

Image Text to Text1.1B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 25, 2026View on Hugging Face ↗
Downloads 30D
5,117
Total downloads
16.1K
Gained 7D
+525(increase)
3.5%(up) vs baseline
Gained 30D
—
Likes
101
+0 in 7D
Rank · tracked models
#11,578
23(down 23 places)this week
Parameters
1.1B
Last source update
Jul 22, 2026
Momentum
53.6
  • HPD-Parsing gained 525 downloads during the last seven tracked days.
  • It moved from #1281 to #1290 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

HPD-Parsing is a image text to text model published by PaddlePaddle. OpenModelStats has tracked the model since Sep 25, 2026, most recently observing it Oct 1, 2026.

Published
Jul 21, 2026
Last updated
Jul 22, 2026
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
1,071,912,960
Spaces
—
Derivative models
—
Velocity 7D/day
75
transformerssafetensorsinternvl_chatfeature-extractionimage-text-to-textvisual-languagepaddleocrdocument-parseHPD-Parsingspeculative-decodingP-MTPeval results

Publisher

PaddlePaddleView publisher statistics →

Derived from OpenGVLab/InternVL3_5-1B (reported by the source; parent not yet tracked).

Similar models

Models similar to HPD-Parsing
ModelDL 30D
Eagle2-1Bnvidia359
InternVL3_5-1BOpenGVLab30.6K
InternVL3_5-1B-HFOpenGVLab13.7K
InternVL3_5-1B-InstructOpenGVLab698
nanoLLaVA-1.5qnguyen3140
aya-vision-8bmobilint368
PaddlePaddle/HPD-Parsing — Downloads, Growth & Stats | OpenModelStats