Args: **p_mask**: (`optional`) ``torch.FloatTensor`` of shape `(batch_size, seq_len)` invalid position mask such as query

Args: One of ``start_states``, ``start_positions`` should be not None. If both are set, ``start_positions`` overrides ``start

Args: One of ``start_states``, ``start_positions`` should be not None. If both are set, ``start_positions`` overrides

hidden_states: float Tensor in shape [bsz, seq_len, hidden_size], the hidden-states of the last layer. cls_index: [optional] position of

Args: x: [n x m1], m1 usually is 2 Outputs: y: [n x m2] m2 dimention

r"""Instantiate a pretrained pytorch model from a pre-trained model configuration. The model is set in evaluation mode by default using ``mod

r""" Instantiate a :class:`~pytorch_transformers.PretrainedConfig` (or a derived class) from a pre-trained model configuration. Parameters:

r""" Instantiate a :class:`~pytorch_transformers.PreTrainedTokenizer` (or a derived class) from a predefined tokenizer. Args:

Implementation of the gelu activation function. For information: OpenAI GPT's gelu is slightly different (and gives slightly different results

Args: module: [nn.module] list or nn.module a list of module to be initialized.

Initialize and prunes weights if needed.

Load tf checkpoints in a pytorch model.

Load tf checkpoints in a pytorch model

Args: x: if the data is constant-length, x is the data tensor with shape (batch, *). Otherwise x is a tuple that

Mask token (string). E.g. when training a model with masked-language modeling. Log an error if used while not having been set.

Id of the mask token in the vocabulary. E.g. when training a model with masked-language modeling. Log an error if used while not having been set.