DEEPSEEK-OCR-2
// Visual Causal Flow
DeepSeek-OCR-2
Visual Causal Flow
13EmergingUnknown
What it does
๐ฅ Model Download | ๐ Paper Link | ๐ Arxiv Paper Link | DeepSeek-OCR 2: Visual Causal Flow Explore more human-like visual encoding. - Install - vLLM Inference - Transformers Inference >Our environment is cuda11.8+torch2.6.0. 1. Clone this repository and navigate to the DeepSeek-OCR-2 folder 2. Conda 3. Packages - download the vllm-0.8.5 whl Note: if you want vLLM and transformers codes to run
Getting Started
git
git clone https://github.com/deepseek-ai/DeepSeek-OCR-2