公开知识图谱记录

Dharma Field Extractor

记录摘要

A 2-billion-parameter model that takes a document image and a request or schema,

来自项目知识图谱的有来源实体；具体工具属性仍需补齐。

基准测试: scored 0.834 on full benchmark covering 546 documents across three request scenarios
能力: Open field extraction without a schema
能力: Schema-directed field extraction matching exact keys and types
能力: extracts exactly the fields you ask for, from any document type, outperforming every frontier LLM we tested, at a fraction of the cost
部署方式: runs self-hosted
语言: English and Portuguese, with a smaller share covering other European and Asian languages
支持类型: input document image, output structured JSON
价格: GPU time on a single L40S at $2.24 per hour

知识图谱当前记录了 13 个已知资料维度，另有 5 个维度尚未记录，关联 1 篇公开资料。这些数字只描述资料覆盖，不代表模型性能或适配性已经验证。