DeepSeek-OCR

核心与官方官方模型与基建中文文档MIT官方缓慢
📥 Model Download | 📄 Paper Link | 📄 Arxiv Paper Link |

功能特性

  • [2026/01/27]🚀🚀🚀🚀🚀🚀 We present DeepSeek-OCR2
  • [2025/10/20]🚀🚀🚀 We release DeepSeek-OCR, a model to investigate the role of vision encoders from an LLM-centric viewpoint.
  • vLLM Inference
  • Transformers Inference
  • download the vllm-0.8.5 whl
  • Transformers

项目预览

相关文档

← 返回 核心与官方 列表