Update app.py

app.py

@@ -5,7 +5,7 @@ from vllm import SamplingParams, LLM
 # Load the model and tokenizer from Hugging Face 
 model_name = "Qwen/Qwen2-7B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-engine = LLM(model="Qwen/Qwen2-7B")
+vllm_model = LLM(model="Qwen/Qwen2-7B")
 
 def generate_response(prompt, max_tokens, temperature, top_p):
     # Tokenize the prompt
@@ -19,7 +19,7 @@ def generate_response(prompt, max_tokens, temperature, top_p):
     )
     
     # Generate text using vLLM
-    output = engine.generate(inputs["input_ids"], sampling_params)
+    output = vllm_model.generate(inputs["input_ids"], sampling_params)
     
     # Decode the generated tokens to text
     generated_text = tokenizer.decode(output[0]["token_ids"], skip_special_tokens=True)