Update README.md

README.md

@@ -20,7 +20,7 @@ Run in a Python pipeline for local inference:
 ```python
 from vllm import LLM, SamplingParams
 
-model = LLM("nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned2.4", sparsity="sparse_w16a16")
+model = LLM("nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned2.4", sparsity="semi_structured_sparse_w16a16")
 prompt = "How to make banana bread?"
 formatted_prompt =  f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"