add deploy using vLLM

README.md

@@ -140,4 +140,9 @@ print(f'User: {question}\nAssistant: {response}')
 #question = "Câu hỏi khác ......"
 #response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
 #print(f'User: {question}\nAssistant: {response}')
+```
+
+Deploying the fine-tuned OCR model as a server:
+```bash 
+!vllm serve TienAnh/Finetune_OCR_1B --port 8000 --dtype=auto
 ```