warnings when inference?

[hildazzz]

i have the following warning when conducting inference, which does it matter? how should i fix it? thanks for your time.

Some weights of the model checkpoint at bert-base-chinese were not used when initializing BertModel: ['cls.predictions.bias', 'c
ls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.bias', 'cls.predictions.transfo
rm.dense.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.decoder.weight', 'cls.predictions.transform.dense.w
eight']
- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another arch
itecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical
(initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
You're using a BertTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than u
sing a method to encode the text followed by a call to the `pad` method to get a padded encoding.
C:\ProgramData\Anaconda3\lib\site-packages\torch\distributions\distribution.py:44: UserWarning: <class 'torch_struct.distributio
ns.TreeCRF'> does not define `arg_constraints`. Please set `arg_constraints = {}` or initialize the distribution with `validate_
args=False` to turn off validation.
  warnings.warn(f'{self.__class__} does not define `arg_constraints`. ' +