Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Convert model weights to safetensors format #308

Closed
cau-git opened this issue Nov 11, 2024 · 3 comments
Closed

Convert model weights to safetensors format #308

cau-git opened this issue Nov 11, 2024 · 3 comments
Assignees
Labels
enhancement New feature or request

Comments

@cau-git
Copy link
Contributor

cau-git commented Nov 11, 2024

We want to move from pickled objects saved by torch or torch.jit to safetensors format for the weights of docling-ibm-models. This has various advantages, such as better security, and also acts as a pre-requisite to achieve proper accelerator support across all models.

@cau-git cau-git added the enhancement New feature or request label Nov 11, 2024
@nikos-livathinos nikos-livathinos self-assigned this Nov 11, 2024
@cau-git
Copy link
Contributor Author

cau-git commented Nov 25, 2024

There is work-in-progess on this PR: DS4SD/docling-ibm-models#50

@davidmezzetti
Copy link

Looking forward to this one! I'm working on a txtai integration for docling and the biggest downside is speed. For some PDFs that are a couple pages it takes 14s to extract vs 200ms with existing methods (Apache Tika). Obviously, the upside is all the formatting being preserved. But if 14s could go down to a couple seconds even it would be a big win.

@nikos-livathinos
Copy link
Collaborator

Docling v2.12.0 has its models in safetensors format: https://github.com/DS4SD/docling/releases/tag/v2.12.0

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

3 participants