Dharma-AI's Gabriel Pimenta ships a 2B model that extracts document fields as JSON

Dharma-AI co-founder Gabriel Pimenta de Freitas Cardoso and three colleagues published the Dharma Field Extractor on November 4th, 2026, a 2-billion-parameter model that takes a document image and returns requested fields typed as JSON. The model was built on Dharma-AI's own OCR model and trained on 43,384 field-level examples, with Paulo Henrique de Medeiros Araujo, Bruno Duarte and Francisco de Almeida Rocha Alves listed as contributors on the Hugging Face announcement. The self-hosted 2B specialist targets high-volume back-office extraction pipelines where per-page frontier API costs compound.

Dharma-AI's Gabriel Pimenta ships a 2B model that extracts document fields as JSON Co-founded by Gabriel Pimenta, Dharma-AI built its 2B extractor on its own OCR model and trained it on 43,384 field-level examples. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published Primary source: Hugging Face Newsroom https://huggingface.co/blog/Dharma-AI/dharma-field-extractor Why it matters Document extraction is a high-volume, measurable task where per-page frontier API costs compound fast. A self-hosted 2B specialist that holds its own on field-level accuracy changes the buying calculation for back-office pipelines, and tests whether Dharma-AI's specialization thesis extends from OCR to structured output. Dharma-AI co-founder Gabriel Pimenta de Freitas Cardoso https://huggingface.co/GabrielPimenta99?ref=runtimewire and three colleagues published the Dharma Field Extractor on November 4th, 2026, a 2-billion-parameter model that takes a document image and returns fields a downstream system asks for, typed as JSON. The announcement on Hugging Face https://huggingface.co/blog/Dharma-AI/dharma-field-extractor?ref=runtimewire lists Paulo Henrique de Medeiros Araujo, Bruno Duarte and Francisco de Almeida Rocha Alves alongside Cardoso as contributors.… When you purchase through links in our articles, we may earn a small commission https://runtimewire.com/affiliate-monetization-standards . This doesn’t affect our editorial independence.