Datalab发布9B开源视觉模型lift，从PDF提取结构化JSON
Datalab Releases lift: A 9B Open-Weights Vision Model That Extracts Structured JSON From PDFs Using Schemas
Datalab的lift模型能自动把PDF转成你需要的JSON格式，准确率90.2%，还不会瞎编字段。
Datalab发布了lift，一个9B参数的开源视觉模型。该模型能将PDF与图像转换为符合给定schema的JSON结构。
它使用schema约束解码确保输出有效，并训练弃权机制避免幻觉，在225份文档的基准上达到90.2%的字段准确率。
Datalab Releases lift: A 9B Open-Weights Vision Model That Extracts Structured JSON From PDFs Using Schemas
Datalab released lift, a 9B open-weights vision model that turns PDFs and images into schema-matching JSON. It uses schema-constrained decoding for valid structure and trained abstention to return null instead of hallucinating absent fields, scoring 90.2% field accuracy on a 225-document benchmark. The post Datalab Releases lift: A 9B Open-Weights Vision Model That Extracts Structured JSON From PDFs Using Schemas appeared first on MarkTechPost .
This report is categorized under AITOP's "Models" desk. Key entities and technical topics under continuous tracking include Datalab, lift, vision models, document parsing.
Primary source verification: published directly by marktechpost with first-party authority.
