DataBubble·
Model Detail
surya-ocr-2
—Provider: datalab-toCategory: multimodalPipeline: image-text-to-text
DB Score
0.0
Downloads
35K
Likes
37
Day
+0.0%
Week
+0.0%
Month
+0.0%
Overview
surya-ocr-2 is a multimodal model with 343M parameters released by datalab-to. The model is registered under the image-text-to-text pipeline tag on Hugging Face, released under the openrail license.
Technical
surya-ocr-2 ships with 343M parameters. Distribution is governed by the openrail license — review the exact terms before commercial deployment.
Use Cases
surya-ocr-2 is best fit for mixed text-and-image reasoning tasks such as document understanding. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Research Paper
Model Info
Licenseopenrail