Update app.py

app.py

@@ -18,7 +18,7 @@ def generate_pred(text):
     with torch.no_grad():
         # generate
         text=f"<s>[INST]<<SYS>>\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n<</SYS>>\n{text}[/INST]"
-        inputs = tokenizer(text, return_tensors="pt").to("cuda")
+        inputs = tokenizer(text, return_tensors="pt") #.to("cuda")
         outputs = model.generate(input_ids=inputs["input_ids"], 
                                  attention_mask=inputs["attention_mask"],
                                  max_new_tokens=1024,