Update app.py

app.py

@@ -70,7 +70,7 @@ def retrieve_context(query):
 # -----------------------------
 # Load Qwen model (CPU only, no accelerate)
 # -----------------------------
-model_name = "Qwen/Qwen2.5-1.5B-Instruct"
+model_name = "meta-llama/Llama-3.2-1B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(