Update README.md

README.md

@@ -77,26 +77,6 @@ response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_token
 print(response)
 ```
 
-### With vLLM
-
-```python
-from vllm import LLM, SamplingParams
-
-llm = LLM(model="Phind/Phind-70B", tensor_parallel_size=4)
-sampling_params = SamplingParams(temperature=0.7, top_p=0.9, max_tokens=1024)
-
-prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
-
-You are Phind, an intelligent assistant that helps with programming and technical questions.<|eot_id|><|start_header_id|>user<|end_header_id|}
-
-Write a Python function to find the longest palindromic substring.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
-
-"""
-
-outputs = llm.generate([prompt], sampling_params)
-print(outputs[0].outputs[0].text)
-```
-
 ## Chat Template
 
 This model uses the Llama 3 chat format: