DeepSeek team open-sources new model DeepSeek-OCR
2025-10-20 10:59:37
The DeepSeek-AI team released the paper "DeepSeek-OCR: Contexts Optical Compression", proposing a new method for compressing long text contexts using visual modes. The Hugging Face page shows that the model has a parameter size of 3B. (Jin Ten)
Disclaimer:
1. The information provided does not constitute investment advice. Investors should make independent decisions and bear all risks themselves.
2. The copyright of this content belongs to the original author. The views expressed herein are solely those of the author and do not represent the stance or position of this website.
Previous article：
DeepSeek团队开源新模型DeepSeek-OCRNext article：
比特币矿业公司比特小鹿科技增持65.6枚BTC，总持有量达到2,126.8枚
