使用 generate 可视化 T5 模型时出现问题

The error I am getting is:

AttributeError Traceback (most recent call last) Cell In[56], line 6 2 decoder_text = tokenizer.convert_ids_to_tokens(outputs.sequences[0])#tokenizer.convert_ids_to_tokens(decoder_input_ids[0]) 5 from bertviz import model_view ----> 6 model_view( 7 encoder_attention=outputs.encoder_attentions, 8 decoder_attention=outputs.decoder_attentions, 9 cross_attention=outputs.cross_attentions, 10 encoder_tokens= encoder_text, 11 decoder_tokens = decoder_text 12 )

File /Volumes/x/envs/my_env/lib/python3.8/site-packages/bertviz/model_view.py:147, in model_view(attention, tokens, sentence_b_start, prettify_tokens, display_mode, encoder_attention, decoder_attention, cross_attention, encoder_tokens, decoder_tokens, include_layers, include_heads, html_action) 145 if include_heads is None: 146 include_heads = list(range(n_heads)) ----> 147 decoder_attention = format_attention(decoder_attention, include_layers, include_heads) 148 attn_data.append( 149 { 150 'name': 'Decoder', ... (...) 154 } 155 ) 156 if cross_attention is not None: File /Volumes/x/envs/my_env/lib/python3.8/site-packages/bertviz/util.py:10, in format_attention(attention, layers, heads) 7 squeezed = [] 8 for layer_attention in attention: 9 # 1 x num_heads x seq_len x seq_len ---> 10 if len(layer_attention.shape) != 4: 11 raise ValueError("The attention tensor does not have the correct number of dimensions. Make sure you set " 12 "output_attentions=True when initializing your model.") 13 ...