Hugging Face Blog·· 6 h ago
Dharma Field Extractor: Any Document In, Structured Fields in JSON Out
Dharma Field Extractor: Any Document In, Structured Fields in JSON Out
AI summary
A 2-billion-parameter model that extracts exactly the fields you ask for, from any document type, outperforming every frontier LLM we tested, at a fraction of the cost.
Selection record
Threshold 60Official, first-handFirst 58Second 58
Not admittedSum of both 116 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：发布2B参数文档字段抽取模型，含训练与评测
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co