Update app.py

app.py

@@ -36,9 +36,17 @@ device = "cuda" # for GPU usage or "cpu" for CPU usage
 tokenizer = AutoTokenizer.from_pretrained(MODEL)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL,
-    torch_dtype=torch.bfloat16,
+    torch_dtype=torch.float16,
+    low_cpu_mem_usage=True,
     device_map="auto")
 
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)
+
 
 
 @spaces.GPU()