Bibstyle-Detector is small language model specialized for the detection of bibliographic style in bibliographic list.
Given a bibliographic entry, Bibstyle-Detector will estimate the most likely style among the 125 most popular styles on Zotero CSL repository.
Like all models published among PleIAs Bad Data Toolbox, Bibstyle-Detector has been volontarily trained on challenging document with a variety of formatting issues. Most of the training corpus comes from the Science-Pile (to be released).
Example
- Downloads last month
- 17
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.