Update app.py

app.py

@@ -7,8 +7,8 @@ model_id = "google/gemma-4-E2B"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    device_map="auto",
-    torch_dtype=torch.float32,
+    device_map={"": "cpu"},
+    dtype=torch.float32,
     low_cpu_mem_usage=True
 )
 
@@ -16,6 +16,7 @@ pipe = pipeline(
     "text-generation",
     model=model,
     tokenizer=tokenizer,
+    device="cpu"
 )
 
 def predict(message, history):