Update app.py

app.py

@@ -19,8 +19,8 @@ embeddings = torch.tensor(df['embedding'].tolist(), device=device)
 model = SentenceTransformer('all-MiniLM-L6-v2', device=device)
 
 # Load the LLaMA model for response generation
-llama_tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
-llama_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct").to(device)
+llama_tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
+llama_model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2").to(device)
 
 # Define the function to find the most relevant document
 def retrieve_relevant_doc(query):