Update README.md

README.md

@@ -22,7 +22,7 @@ Run in a Python pipeline for local inference:
 ```python
 from vllm import LLM, SamplingParams
 
-model = LLM("nm-testing/llama2.c-stories110M-pruned2.4", sparsity="sparse_w16a16")
+model = LLM("nm-testing/llama2.c-stories110M-pruned2.4", sparsity="semi_structured_sparse_w16a16")
 prompt = "My name is "
 sampling_params = SamplingParams(max_tokens=100,temperature=0)
 outputs = model.generate(prompt, sampling_params=sampling_params)