Dharma Field Extractor 将文档图像转换为结构化 JSON

发生了什么

Dharma-AI 推出了 Dharma Field Extractor，这是一款拥有 20 亿参数的模型，可将文档图像转换为结构化 JSON：既可以提取它识别出的字段，也可以按照用户指定的架构填充字段。作者报告称，该模型在 1,638 个基准测试案例中得分为 0.834，高于测试的四种前沿配置；与所比较的 API 相比，自托管 GPU 成本低 6 至 147 倍。

接下来读什么

• 今日还有哪些重要变化Hugging Face 提议为 Transformers 制定模型集成契约

这件事到目前为止

Dharma-AI introduced the Dharma Field Extractor, a 2-billion-parameter model that turns document images into structured JSON by either extracting fields it identifies or filling a schema supplied by the user. The model is now available for those two extraction workflows. The authors reported a score of 0.834 across 1,638 benchmark cases, higher than four frontier configurations they tested. They also reported that self-hosting the model on GPUs cost 6 to 147 times less than the compared APIs.