Update README.md

README.md

@@ -19,6 +19,7 @@ tags:
 - text-generation-inference
 - VLM
 - Callisto
+- OCR#3
 ---
 
 ![xfghnbfgt.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/dblNhOatHlsLemn1Yt_zo.png)
@@ -136,4 +137,4 @@ for new_text in streamer:
    - Designed to handle **multi-turn interactions**, providing context-aware responses.
 
 6. **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.