Update app.py

app.py

@@ -25,8 +25,8 @@ index.add(embeddings)
 sentence_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2', device=device)
 
 # Load the LLaMA model for response generation
-llama_tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
-llama_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf").to(device)
+llama_tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
+llama_model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2").to(device)
 
 # Load the summarization model
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn", device=0 if device == 'cuda' else -1)