Update app.py

app.py

@@ -8,10 +8,12 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 #model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto")
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
-    device_map={"": "cpu"},
+    device_map="auto",              # Hugging Face accelerate use karega
+    offload_folder="offload",       # Disk pe offload karega (RAM bachi rahegi)
     low_cpu_mem_usage=True,
     trust_remote_code=True
 )
+
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)