Update generate.py

generate.py

@@ -15,6 +15,7 @@ def generate(model, input_ids, generation_config, left_padding=None, **kwargs):
         batch_size = input_ids.shape[0]
         pad_tensor = torch.full(size=(batch_size, left_padding), fill_value=pad_token).to(input_ids.device)
         input_ids = torch.cat((pad_tensor, input_ids), dim=1)
+        cur_length = input_ids.shape[1]
 
     # Simple greedy decoding loop
     while cur_length < max_length: