Getting error in Summarize Dialogue without Prompt Engineering

Course Q&A Generative AI with Large Language Models
1

When I try to execute following code:

for i, index in enumerate(example_indices):
    dialogue = dataset['test'][index]['dialogue']
    summary = dataset['test'][index]['summary']
    print("dial"+dialogue)
    print("summ"+summary)
    inputs = tokenizer(dialogue, return_tensors='pt')
    print("inputs {}".format(len(inputs["input_ids"][0])))
    output = tokenizer.decode(
        model.generate(
            inputs["input_ids"], 
            max_new_tokens=50,
        )[0],
        skip_special_tokens=True
    )

    print(dash_line)
    print('Example ', i + 1)
    print(dash_line)
    print(f'INPUT PROMPT:\n{dialogue}')
    print(dash_line)
    print(f'BASELINE HUMAN SUMMARY:\n{summary}')
    print(dash_line)
    print(f'MODEL GENERATION - WITHOUT PROMPT ENGINEERING:\n{output}\n')

Get the following error:

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
/tmp/ipykernel_10219/2036297124.py in <module>
      9         model.generate(
     10             inputs["input_ids"],
---> 11             max_new_tokens=50,
     12         )[0],
     13         skip_special_tokens=True

~/anaconda3/envs/amazonei_pytorch_latest_p37/lib/python3.7/site-packages/torch/autograd/grad_mode.py in decorate_context(*args, **kwargs)
     13         def decorate_context(*args, **kwargs):
     14             with self:
---> 15                 return func(*args, **kwargs)
     16         return decorate_context
     17 

~/anaconda3/envs/amazonei_pytorch_latest_p37/lib/python3.7/site-packages/transformers/generation/utils.py in generate(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, **kwargs)
   1413                 return_dict_in_generate=generation_config.return_dict_in_generate,
   1414                 synced_gpus=synced_gpus,
-> 1415                 **model_kwargs,
   1416             )
   1417 

~/anaconda3/envs/amazonei_pytorch_latest_p37/lib/python3.7/site-packages/transformers/generation/utils.py in greedy_search(self, input_ids, logits_processor, stopping_criteria, max_length, pad_token_id, eos_token_id, output_attentions, output_hidden_states, output_scores, return_dict_in_generate, synced_gpus, **model_kwargs)
   2250             if eos_token_id_tensor is not None:
   2251                 unfinished_sequences = unfinished_sequences.mul(
-> 2252                     next_tokens.tile(eos_token_id_tensor.shape[0], 1).ne(eos_token_id_tensor.unsqueeze(1)).prod(dim=0)
   2253                 )
   2254 

AttributeError: 'Tensor' object has no attribute 'tile'

Can someone please guide how to resolve this?

2

If you havent changed anything in this cell, have you perhaps forgotten to run any of the previous cells of code?!