Update README.md

README.md

@@ -127,7 +127,7 @@ with torch.no_grad():
         for k in ['input_ids', 'attention_mask']:
             model_input[k] = torch.tensor(batch[k]).to('cuda')
 
-        output_ids = ft_model.generate(**model_input,
+        output_ids = lama2dictionary.generate(**model_input,
                                        max_length = max_length * batch_size,
                                        forced_eos_token_id = eos_tokens,
                                        max_time = max_time * batch_size,