Skip to content
EVENT / TOPICActive

Dharma-AI Releases 2B-Parameter Dharma Field Extractor for Document-to-JSON Extraction

1 reports1 sources11/4/2026 updated

Current overview (not historical)

AI overview

Dharma-AI has released Dharma Field Extractor, a 2-billion-parameter model that converts document images into typed, structured JSON by extracting fields either on open request or according to a user-specified schema. The model works on arbitrary document images and returns results aligned with the document’s own nesting structure. Dharma-AI said the model accepts document images and allows users to request all discoverable fields or provide an exact schema for the model to fill. It returns fields one by one with types, following the nesting relationships found in the document.

Written with AI from the reporting · updated 11/4/2026

Explore the timeline, relations and evidence
Expand the detailed fact route and sources

Story route

A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.

  1. 1Unclassified fact stationNov 5, 02:50single sourcereport-time onlyrevised

    Hugging Face 发布 Dharma 文档字段提取模型

    Read original source ↗ Hugging Face BlogReplay this moment in the explorer
    Evidence & revisions · 1 source records
    Subject：
    hugging-face
    Action：
    发布
    Object：
    Dharma Field Extractor 20 亿参数文档字段提取模型
    Occurred (fact side)：
    not recorded
    Hugging Face Blog ↗Report pageRevision 2 · currently revised
    Published (valid side)：
    Nov 5, 01:50
    First seen (known side)：
    Nov 5, 02:50
    Fact stationSingle source · one-sided claimRevisedReport-time only

    Copy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.

Uncertainty marks flag where to check the sources; they are not proven causation.

Report timeline

Explore every side through dated source reports.

Nov 5
  1. Hugging Face BlogSelectedFirst-party sourceRelated fact: single sourceFact occurrence time unverifiedSource report revised
    Dharma Field Extractor: Any Document In, Structured Fields in JSON Out

    Report first recorded Nov 5, 02:50

    Read original source ↗

Event activity trend

Latest comparable
8
Comparable peak
10Nov 5, 03:00
24h change
–

The chart compares consistently observed participants only. Hover or tap to inspect each hour; use arrow keys to move between observations.

Event discussion

Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.

Open GitHub Discussions