{"slug": "dharma-ai-s-gabriel-pimenta-ships-a-2b-model-that-extracts-document-fields-as", "title": "Dharma-AI's Gabriel Pimenta ships a 2B model that extracts document fields as JSON", "summary": "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.", "body_md": "# Dharma-AI's Gabriel Pimenta ships a 2B model that extracts document fields as JSON\n\n**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.**\n\n        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)\n        · Published \n\nPrimary source: [Hugging Face Newsroom](https://huggingface.co/blog/Dharma-AI/dharma-field-extractor)\n\n## Why it matters\n\nDocument 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.\n\nDharma-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.…\n\nWhen 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.", "url": "https://wpnews.pro/news/dharma-ai-s-gabriel-pimenta-ships-a-2b-model-that-extracts-document-fields-as", "canonical_source": "https://runtimewire.com/article/dharma-ai-field-extractor-2b-json", "published_at": "2026-11-04 17:58:28+00:00", "updated_at": "2026-11-04 21:19:28.849536+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-products", "ai-tools", "computer-vision"], "entities": ["Dharma-AI", "Gabriel Pimenta de Freitas Cardoso", "Dharma Field Extractor", "Hugging Face", "Paulo Henrique de Medeiros Araujo", "Bruno Duarte", "Francisco de Almeida Rocha Alves"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/dharma-ai-s-gabriel-pimenta-ships-a-2b-model-that-extracts-document-fields-as", "markdown": "https://wpnews.pro/news/dharma-ai-s-gabriel-pimenta-ships-a-2b-model-that-extracts-document-fields-as.md", "text": "https://wpnews.pro/news/dharma-ai-s-gabriel-pimenta-ships-a-2b-model-that-extracts-document-fields-as.txt", "jsonld": "https://wpnews.pro/news/dharma-ai-s-gabriel-pimenta-ships-a-2b-model-that-extracts-document-fields-as.jsonld"}}