NVIDIA Nemotron Parse 1.1

摘要

我們推出 Nemotron-Parse-1.1，這款輕量級文件解析與OCR模型在其前身 Nemoretriever-Parse-1.0 的基礎上實現了能力升級。該模型在通用OCR、Markdown格式解析、結構化表格解析，以及從圖片、圖表與圖示中提取文字等方面均有所提升，並支援更長的輸出序列長度以處理視覺密集型文件。承襲前代特性，它能提取文字區塊的邊界框及對應語義類別。Nemotron-Parse-1.1採用編碼器-解碼器架構，參數量達8.85億，其中包含精簡的2.56億參數語言解碼器。在公開基準測試中展現極具競爭力的準確度，成為強大的輕量級OCR解決方案。我們已於Huggingface平台公開發布模型權重、優化的NIM容器，並隨Nemotron-VLM-v2數據集釋出部分訓練資料。同時推出視覺標記長度縮減的Nemotron-Parse-1.1-TC版本，在幾乎不影響品質的前提下實現20%的速率提升。

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.