Update app.py

app.py

@@ -3,9 +3,9 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from vllm import LLM, SamplingParams
 
 # Load the model and tokenizer from Hugging Face 
-model_name = "Qwen/Qwen2-0.5B"
+model_name = "facebook/opt-125m"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-vllm_model = LLM(model="Qwen/Qwen2-0.5B")
+vllm_model = LLM(model="facebook/opt-125m")
 
 def generate_response(prompt, max_tokens, temperature, top_p):
     # Tokenize the prompt