Update app.py

app.py

@@ -12,12 +12,10 @@ vllm_model = LLM(model=model_name, tensor_parallel_size=1, device="cpu")
 
  
 
-def generate_response(prompt, max_tokens, temperature, top_p):
+def generate_response(prompt ):
     # Define sampling parameters
     sampling_params = SamplingParams(
-        max_tokens=max_tokens,
-        temperature=temperature,
-        top_p=top_p,
+         
     )
     
     # Generate text using vLLM (input is the raw string `prompt`)
@@ -31,10 +29,8 @@ def generate_response(prompt, max_tokens, temperature, top_p):
 
  
 prompt =gr.Textbox()
-max_tokens = gr.Textbox()
-temperature = gr.Textbox()
-top_p = gr.Textbox()
-demo=gr.Interface(generate_response, inputs=[prompt, max_tokens,temperature, top_p], outputs="text")
+ 
+demo=gr.Interface(generate_response, inputs=[prompt ], outputs="text")
 
 # Launch the app
 demo.launch()