轻量级文档解析模型，支持多类型内容高效提取
NVIDIA Nemotron Parse 1.1
- 采用编码器-解码器架构，885M参数，语言解码器256M
- 在公开基准上表现优异，支持长序列输出与复杂图文解析
- 提供加速版模型，速度提升20%且质量损失小，适合部署
我们提出Nemotron-Parse-1.1，一种轻量级文档解析与OCR模型，相较于前代Nemoretriever-Parse-1.0有全面升级。该模型在通用OCR、Markdown格式化、结构化表格解析及图片、图表和示意图中的文本提取方面表现更优，并支持对视觉密集型文档的更长输出序列。与前代一致，可提取文本段落的边界框及其语义类别。模型采用编码器-解码器架构，共885M参数，其中语言解码器为256M参数。在公共基准上达到竞争性准确率，是优秀的轻量级OCR解决方案。我们已在Huggingface公开模型权重，同时提供优化的NIM容器及部分训练数据（作为Nemotron-VLM-v2数据集的一部分）。此外，还发布Nemotron-Parse-1.1-TC版本，通过减少视觉标记长度实现20%的速度提升，质量损失极小。
原文摘要 · Abstract (English)
We introduce Nemotron-Parse-1.1, a lightweight document parsing and OCR model that advances the capabilities of its predecessor, Nemoretriever-Parse-1.0. Nemotron-Parse-1.1 delivers improved capabilities across general OCR, markdown formatting, structured table parsing, and text extraction from pictures, charts, and diagrams. It also supports a longer output sequence length for visually dense documents. As with its predecessor, it extracts bounding boxes of text segments, as well as corresponding semantic classes. Nemotron-Parse-1.1 follows an encoder-decoder architecture with 885M parameters, including a compact 256M-parameter language decoder. It achieves competitive accuracy on public benchmarks making it a strong lightweight OCR solution. We release the model weights publicly on Huggingface, as well as an optimized NIM container, along with a subset of the training data as part of the broader Nemotron-VLM-v2 dataset. Additionally, we release Nemotron-Parse-1.1-TC which operates on a reduced vision token length, offering a 20% speed improvement with minimal quality degradation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。