update info metadata (#3)

- update info metadata (0e41c4dc975513db00e1dabc705fee89ee44c290)

README.md

@@ -18,7 +18,12 @@ tags:
 - vl
 - qwen2_vl
 - 2B
+- VQA
+- KIE
+- Latex
 ---
+# **Qwen2-VL-OCR2-2B-Instruct [ VL / OCR ]**
+
 ![OCR2.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/o6jr8Vl_Spy9IAxutAB3j.png)
 
 # **Qwen2-VL-OCR2-2B-Instruct**
@@ -126,4 +131,4 @@ print(output_text)
    - Designed to handle **multi-turn interactions**, providing context-aware responses.
 
 5. **Image-Text-to-Text Generation:**  
-   - Inputs can include **images, text, or a combination**, and the model generates descriptive or problem-solving text.
+   - Inputs can include **images, text, or a combination**, and the model generates descriptive or problem-solving text.