Update app.py

app.py

@@ -5,14 +5,14 @@ import gradio as gr
 model_id = "witfoo/witq-1.0"
 dtype = torch.float16 # float16 for Tesla T4, V100, bfloat16 for Ampere+ 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
+# Use GPU if available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     torch_dtype=dtype,
-    device_map="auto",
+    device_map=device,
 )
-# Use GPU if available
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model.to(device)
+
 
 preamble = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request."