AttributeError: 'XLNetConfig' object has no attribute 'absa_tagger_config'

[davidlenz]

Hi, thanks for the great repo!

Bert runs very well for me, however when switching to XLNET i constantly get this error.

error:

Traceback (most recent call last):
  File "main.py", line 522, in <module>
    main()
  File "main.py", line 412, in main
    config=config, cache_dir='./cache')
  File "C:\Anaconda3\envs\py37_dev\lib\site-packages\transformers\modeling_utils.py", line 342, in from_pretrained
    model = cls(config, *model_args, **model_kwargs)
  File "\BERT-E2E-ABSA\absa_layer.py", line 488, in __init__
    self.tagger_config = xlnet_config.absa_tagger_config
AttributeError: 'XLNetConfig' object has no attribute 'absa_tagger_config'

heres my train.bat:

#!/usr/bin/env bash
set TASK_NAME="rest_total"
set ABSA_TYPE="tfm"
set CUDA_VISIBLE_DEVICES=0 
python main.py --model_type xlnet ^
                         --absa_type %ABSA_TYPE% ^
                         --tfm_mode finetune ^
                         --fix_tfm 0 ^
                         --model_name_or_path xlnet-base-cased ^
                         --data_dir ./data/sents ^
                         --task_name %TASK_NAME% ^
                         --per_gpu_train_batch_size 16 ^
                         --per_gpu_eval_batch_size 8 ^
                         --learning_rate 2e-5 ^
                         --do_train ^
                         --do_eval ^
                         --tagging_schema BIEOS ^
                         --overfit 0 ^
                         --overwrite_output_dir ^
                         --eval_all_checkpoints ^
                         --MASTER_ADDR localhost ^
                         --MASTER_PORT 28512 ^
                         --max_steps 2000

am running transformers 2.0.0 as per the requirements.

>>> import transformers as t
>>> t.__version__
'2.0.0'

[lixin4ever]

Thank you for your attention. The implementation of XLNetABSATagger is incomplete (and thus you cannot run normally). The reason I do not continue to add this feature is that the model based on XLNet performs quite poor on ABSA datasets. I am not sure if I miss some important details. Considering your case, you can write a new XLNetABSATagger class following the style of BertABSATagger and check whether it works or not.

[davidlenz]

Thank your for your Feedback!