Update app.py

app.py

@@ -2,10 +2,9 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from vllm import SamplingParams, LLM
 
-# Load the model and tokenizer from Hugging Face
-model_name = "Qwen/Qwen2-7B"  
+# Load the model and tokenizer from Hugging Face 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-engine = LLM.from_pretrained(model_name)
+engine = LLM(model="Qwen/Qwen2-7B")
 
 def generate_response(prompt, max_tokens, temperature, top_p):
     # Tokenize the prompt