Update README.md

README.md

@@ -59,8 +59,8 @@ if __name__ == '__main__':
     tokenizer = AutoTokenizer.from_pretrained("inclusionAI/Ring-mini-linear-2.0-GPTQ-int4")
     
     sampling_params = SamplingParams(temperature=0.6, top_p=1.0, max_tokens=16384)
-    
-    
+
+    # use `max_num_seqs=1` without concurrency
     llm = LLM(model="inclusionAI/Ring-mini-linear-2.0-GPTQ-int4", dtype='auto', enable_prefix_caching=False, max_num_seqs=128)
     
     
@@ -76,7 +76,7 @@ if __name__ == '__main__':
     )
     outputs = llm.generate([text], sampling_params)
     for output in outputs:
-        print(output.outputs.)
+        print(output.outputs[0].text)
 ```
 
 #### Online Inference