Method from_pretrained

model/modeling_bert.py:718–849

Instantiate a PreTrainedBertModel from a pre-trained model file or a pytorch state dict. Download and cache the pre-trained model file if needed. Params: pretrained_model_name: either: - a str with the name of a pre-trained model to load selected

(cls, pretrained_model_name, state_dict=None, cache_dir=None,
                        fp32_layernorm=False, fp32_embedding=False, layernorm_epsilon=1e-12,
                        fp32_tokentypes=False, *inputs, **kwargs)

    @classmethod
    def from_pretrained(cls, pretrained_model_name, state_dict=None, cache_dir=None,
                        fp32_layernorm=False, fp32_embedding=False, layernorm_epsilon=1e-12,
                        fp32_tokentypes=False, *inputs, **kwargs):
        """
        Instantiate a PreTrainedBertModel from a pre-trained model file or a pytorch state dict.
        Download and cache the pre-trained model file if needed.

        Params:
            pretrained_model_name: either:
                - a str with the name of a pre-trained model to load selected in the list of:
                    . `bert-base-uncased`
                    . `bert-large-uncased`
                    . `bert-base-cased`
                    . `bert-large-cased`
                    . `bert-base-multilingual-uncased`
                    . `bert-base-multilingual-cased`
                    . `bert-base-chinese`
                - a path or url to a pretrained model archive containing:
                    . `bert_config.json` a configuration file for the model
                    . `pytorch_model.bin` a PyTorch dump of a BertForPreTraining instance
            cache_dir: an optional path to a folder in which the pre-trained models will be cached.
            state_dict: an optional state dictionnary (collections.OrderedDict object) to use instead of Google pre-trained models
            *inputs, **kwargs: additional input for the specific Bert class
                (ex: num_labels for BertForSequenceClassification)
        """
        if pretrained_model_name in PRETRAINED_MODEL_ARCHIVE_MAP:
            archive_file = PRETRAINED_MODEL_ARCHIVE_MAP[pretrained_model_name]
        else:
            archive_file = pretrained_model_name
        # redirect to the cache, if necessary
        try:
            resolved_archive_file = cached_path(archive_file, cache_dir=cache_dir)
        except FileNotFoundError:
            logger.error(
                "Model name '{}' was not found in model name list ({}). "
                "We assumed '{}' was a path or url but couldn't find any file "
                "associated to this path or url.".format(
                    pretrained_model_name,
                    ', '.join(PRETRAINED_MODEL_ARCHIVE_MAP.keys()),
                    archive_file))
            return None
        if resolved_archive_file == archive_file:
            logger.info("loading archive file {}".format(archive_file))
        else:
            logger.info("loading archive file {} from cache at {}".format(
                archive_file, resolved_archive_file))
        tempdir = None
        if os.path.isdir(resolved_archive_file):
            serialization_dir = resolved_archive_file
        else:
            # Extract archive to temp dir
            tempdir = tempfile.mkdtemp()
            logger.info("extracting archive file {} to temp dir {}".format(
                resolved_archive_file, tempdir))
            with tarfile.open(resolved_archive_file, 'r:gz') as archive:
                def is_within_directory(directory, target):
                    
                    abs_directory = os.path.abspath(directory)