Nanonets-OCR-s – OCR model transforms documents into structured markdown

Re:Nanonets-OCR-s – OCR model transforms documents into stru... by souvik3333 on Monday June 16, 2025 @02:56AM (#44287216)

Hi, author of the model here. It is an open-weight model, you can download it from here: https://huggingface.co/nanonets/Nanonets-OCR-s

[ Parent | on HN ]

Re:Nanonets-OCR-s – OCR model transforms documents into stru... by gardnr on Monday June 16, 2025 @04:09AM (#44287546)

Interestingly, another OCR model based on Qwen2.5-VL-3B just dropped which also publishes as Apache 2. It's right next to Nanonets-OCR-s on the HF "Trending" list.

https://huggingface.co/echo840/MonkeyOCR/blob/main/Recogniti...

[ Parent | on HN ]

Re:Nanonets-OCR-s – OCR model transforms documents into stru... by CaptainFever on Monday June 16, 2025 @11:47AM (#44290708)

IMO weights being downloadable doesn't mean it's open weight.

My understanding:

    - Weight available: You can download the weights.
    - Open weight: You can download the weights, and it is licensed freely (e.g. public domain, CC BY-SA, MIT).
    - Open source: (Debated) You can download the weights, it is licensed freely, and the training dataset is also available and licensed freely.

For context:

> You're right. The Apache-2.0 license was mistakenly listed, and I apologize for the confusion. Since it's a derivative of Qwen-2.5-VL-3B, it will have the same license as the base model (Qwen RESEARCH LICENSE AGREEMENT). Thanks for pointing this out.

[ Parent | on HN ]