Update README.md

README.md

@@ -1,4 +1,11 @@
 ---
+language:
+- multilingual
+tags:
+- deepseek
+- vision-language
+- ocr
+- document-parse
 base_model:
 - deepseek-ai/DeepSeek-OCR
 ---
@@ -7,6 +14,15 @@ base_model:
 > [!NOTE]  
 > Note currently only [NexaSDK](https://github.com/NexaAI/nexa-sdk) supports this model's GGUF.
 
+## Quickstart
+
+1. **Install [NexaSDK](https://github.com/NexaAI/nexa-sdk)**
+2. Run the model locally with one line of code:
+
+   ```bash
+   nexa infer NexaAI/DeepSeek-OCR-GGUF
+   ```
+
 ## Model Description
 **DeepSeek OCR** is a high-accuracy optical character recognition model built for extracting text from complex visual inputs such as documents, screenshots, receipts, and natural scenes.  
 It combines vision-language modeling with efficient visual encoders to achieve superior recognition of multi-language and multi-layout text while remaining lightweight enough for edge or on-device deployment.
@@ -15,7 +31,7 @@ It combines vision-language modeling with efficient visual encoders to achieve s
 - **Multilingual OCR** — recognizes printed and handwritten text across major global languages.  
 - **Document Layout Understanding** — preserves structure such as tables, paragraphs, and titles.  
 - **Scene Text Recognition** — robust against lighting, distortion, and low-quality captures.  
-- **Lightweight & Fast** — optimized for CPU, GPU, and NPU acceleration.  
+- **Lightweight & Fast** — optimized for CPU and GPU acceleration.  
 - **End-to-End Pipeline** — supports image-to-text and structured JSON output.  
 
 ## Use Cases
@@ -38,7 +54,6 @@ It combines vision-language modeling with efficient visual encoders to achieve s
 DeepSeek OCR can be integrated through:  
 - Python API (`pip install deepseek-ocr`)  
 - REST or gRPC endpoints for server deployment  
-- On-device SDKs optimized for NPUs (via NexaSDK, OpenVINO, or TensorRT)  
 
 ## License
 This model is released under the **Apache 2.0 License**, allowing commercial use, modification, and redistribution with attribution.