Update app.py

app.py

@@ -4,8 +4,12 @@ import os
 import wntr
 from transformers import pipeline
 
-# Load LLM
-llm = pipelinepipeline("text-generation", model="Qwen/Qwen2.5-7B-Instruct-1M")
+@st.cache_resource
+def load_llm():
+    model_name = "Qwen/Qwen2.5-7B-Instruct-1M"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+    return pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 st.title("💧 EPANET + LLM (via WNTR + Qwen LLM)")