Update README.md

README.md

@@ -104,3 +104,32 @@ if __name__ == "__main__":
 
     trainer.save_model(training_args.output_dir)
 ```
+
+### Test Script
+```python
+from vllm import LLM
+from datasets import load_dataset
+from vllm.sampling_params import SamplingParams
+from transformers import AutoTokenizer
+
+MODEL_PATH = "autodl-tmp/saves/Qwen2.5-1.5B-ultrachat200k"
+
+model = LLM(MODEL_PATH,
+            tensor_parallel_size=1,
+            dtype='bfloat16')
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+
+input = tokenizer.apply_chat_template([{"role": "user", "content": "Which province is Shenyang in?"}],
+                                    tokenize=False,
+                                    add_generation_prompt=True)
+sampling_params = SamplingParams(max_tokens=1024,
+                                 temperature=0.7,
+                                 logprobs=1,
+                                 stop_token_ids=[tokenizer.eos_token_id])
+
+vllm_generations = model.generate(input,
+                                  sampling_params)
+
+print(vllm_generations[0].outputs[0].text)
+# print result: Shenyang is in Liaoning province, China.
+```