Update app.py

app.py

@@ -60,7 +60,7 @@ def generate_sql(query,context):
   prompt = query
   context=context
   text=f"<s>##Question: {prompt} \n ##Context: {context} \n ##Answer:"
-  inputs=tokenizer(text,return_tensors='pt').to('cuda')
+  inputs=tokenizer(text,return_tensors='pt').to('cpu')
   with torch.no_grad():
     outputs=model.generate(**inputs,max_new_tokens=100,do_sample=True,top_p=0.99,top_k=10,temperature=0.5)
   output_text=outputs[:, inputs.input_ids.shape[1]:]