Downloads · 30 days
93
1% of all-time downloads
tngtech/olmOCR-7B-faithful
olmOCR-7B-faithful is a image-text-to-text model from tngtech. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
This is a fine-tuned version of the olmOCR-7B-0225-preview model that aims to extract all information from a given document, including header and footer information.
Downloads · 30 days
93
1% of all-time downloads
All-time downloads
11.8K
Public
Parameters
8.3B
33.2 GB on disk
Likes
18
Public
Click a slice to open those files.
.safetensors16.6 GB · 100%
From the Hugging Face model README
This is a fine-tuned version of the olmOCR-7B-0225-preview model that aims to extract all information from a given document, including header and footer information.
More information on how we fine-tuned the model can be found in our blog post.
We thank the Allen Institute for AI and Alibaba Cloud for their great open-source work, which enabled this fine-tuning project.
Improved using Qwen.