cmboulanger/tei-bibl-annotator-citext

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 27, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

The cmboulanger/tei-bibl-annotator is a 3.1 billion parameter LoRA fine-tune of Qwen/Qwen2.5-3B-Instruct, designed to tag plain-text bibliographic citations with inline TEI XML markup. This model precisely reproduces input text, inserting tags for bibliographic structure like author, title, and date, without paraphrasing or normalization. It specializes in annotating complex citations from legal-sociology scholarship, including short-form and anaphoric references, making it ideal for structured bibliographic data extraction.

Loading preview...

TEI Bibliographic Annotator

This model, cmboulanger/tei-bibl-annotator, is a LoRA fine-tune of the 3.1 billion parameter Qwen/Qwen2.5-3B-Instruct base model. Its primary function is to accurately tag plain-text bibliographic citations with inline TEI XML markup. A key feature is its ability to reproduce the input text exactly, inserting XML tags around structural elements such as author, title, date, and publisher, without altering or normalizing the original citation.

Key Capabilities

  • Precise TEI XML Tagging: Annotates bibliographic citations with TEI XML, preserving the original text content.
  • Handles Complex Citations: Trained on footnotes from legal-sociology scholarship, it effectively processes short-form, anaphoric, and mixed-prose citations.
  • High Parse Success: Achieved 99.83% parse success (valid TEI XML) on a held-out development set.
  • Instruction-tuned: Expects a fixed system instruction and the raw citation as user input, following the Qwen/Qwen2.5-3B-Instruct chat prompt format.

Good For

  • Structured Data Extraction: Ideal for converting unstructured bibliographic text into machine-readable TEI XML.
  • Digital Humanities Projects: Useful for researchers working with historical or academic texts requiring detailed citation analysis.
  • Legal and Academic Research: Particularly effective for processing citations found in legal-sociology scholarship, including challenging footnote formats.

Note: This model is for research use only and inherits the Qwen Research License from its base model, which restricts commercial use.

Finetunes
2 models