huggingface / huggingface/candle

SmolDocling model support

Open
#2,933 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Rust
Stars
21k
Forks
1.8k
Avg merge
16h 42m
Merged PRs (30d)
25

Description

Would there be any interest in adding this model?

https://huggingface.co/ds4sd/SmolDocling-256M-preview

I toyed around with an implementation last night but most of my experience has been with text models and am new to vision models, so it's not quite working yet

If there's any interest in adding it I can keep trying to grind it out! If anyone could give me some help/advice that would be great as well!

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the SmolDocling-256M-preview model page linked in the issue and review Candle's existing model integrations for a suitable entry point. The issue names no files or tests; success would require working SmolDocling support and a clear way to verify that the vision model runs.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, rust
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.