Update README.md

README.md

@@ -24,7 +24,6 @@ os.environ['VLLM_ATTENTION_BACKEND'] = 'FLASHINFER'
 
 from transformers import AutoTokenizer
 from gptqmodel import BACKEND, GPTQModel
-from vllm import SamplingParams
 
 model_name = "ModelCloud/gemma-2-27b-it-gptq-4bit"
 
@@ -37,15 +36,7 @@ model = GPTQModel.from_quantized(
             backend=BACKEND.VLLM,
         )
 
-sampling_params = SamplingParams(temperature=0.95, max_tokens=128)
-
 inputs = tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True)
-
-outputs = model.generate(
-            prompts=inputs,
-            sampling_params=sampling_params,
-        )
-
+outputs = model.generate(prompts=inputs,)
 print(outputs[0].outputs[0].text)
-
 ```