transformers/main/ko/internal/modeling_utils.md

사용자 정의 레이어 및 유틸리티 [[custom-layers-and-utilities]]

이 페이지는 라이브러리에서 사용되는 사용자 정의 레이어와 모델링을 위한 유틸리티 함수들을 나열합니다.

이 함수들 대부분은 라이브러리 내의 모델 코드를 연구할 때만 유용합니다.

PyTorch 사용자 정의 모듈 [[transformers.Conv1D]][[transformers.Conv1D]]

transformers.Conv1D[[transformers.Conv1D]]

transformers.Conv1D(nf, nx)

Source

Parameters:

nf (int) : The number of output features.

nx (int) : The number of input features.

1D-convolutional layer as defined by Radford et al. for OpenAI GPT (and also used in GPT-2).

Basically works like a linear layer but the weights are transposed.

PyTorch 헬퍼(helper) 함수 [[transformers.apply_chunking_to_forward]][[transformers.apply_chunking_to_forward]]

transformers.apply_chunking_to_forward[[transformers.apply_chunking_to_forward]]

transformers.apply_chunking_to_forward(forward_fn: Callable[..., torch.Tensor], chunk_size: int, chunk_dim: int, *input_tensors)

Source

Parameters:

forward_fn (Callable[..., torch.Tensor]) : The forward function of the model.

chunk_size (int) : The chunk size of a chunked tensor: num_chunks = len(input_tensors[0]) / chunk_size.

chunk_dim (int) : The dimension over which the input_tensors should be chunked.

input_tensors (tuple[torch.Tensor]) : The input tensors of forward_fn which will be chunked

Returns: torch.Tensor

A tensor with the same shape as the forward_fn would have given if applied`.

This function chunks the input_tensors into smaller input tensor parts of size chunk_size over the dimension chunk_dim. It then applies a layer forward_fn to each chunk independently to save memory.

If the forward_fn is independent across the chunk_dim this function will yield the same result as directly applying forward_fn to input_tensors.

Examples:

# rename the usual forward() fn to forward_chunk()
def forward_chunk(self, hidden_states):
    hidden_states = self.decoder(hidden_states)
    return hidden_states

# implement a chunked forward function
def forward(self, hidden_states):
    return apply_chunking_to_forward(self.forward_chunk, self.chunk_size_lm_head, self.seq_len_dim, hidden_states)

transformers.pytorch_utils.prune_linear_layer[[transformers.pytorch_utils.prune_linear_layer]]

transformers.pytorch_utils.prune_linear_layer(layer: nn.Linear, index: torch.LongTensor, dim: int = 0)

Source

Parameters:

layer (torch.nn.Linear) : The layer to prune.

index (torch.LongTensor) : The indices to keep in the layer.

dim (int, optional, defaults to 0) : The dimension on which to keep the indices.

Returns: torch.nn.Linear

The pruned layer as a new layer with requires_grad=True.

Prune a linear layer to keep only entries in index.

Used to remove heads.