Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from vllm import SamplingParams, LLM
+from vllm import LLM, SamplingParams
 
 # Load the model and tokenizer from Hugging Face 
-model_name = "Qwen/Qwen2-7B"
+model_name = "Qwen/Qwen2-0.5B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-vllm_model = LLM(model="Qwen/Qwen2-7B")
+vllm_model = LLM(model="Qwen/Qwen2-0.5B")
 
 def generate_response(prompt, max_tokens, temperature, top_p):
     # Tokenize the prompt