See `AutoTokenizer.from_pretrained` docstring.

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be

Appends dimensions to the end of a tensor until it has target_dims dimensions.

Create a 1D, 2D, or 3D convolution module.

Create a linear module.

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

Turn a ResNetBlock into a sequence of tasks and append to the task queue @param queue: the target task queue @param block: ResNetBlock

Zero out the parameters of a module and return it.

[N, C], [-1, 1], RGB

Disable the redundant torch default initialization to accelerate model creation.

[N, C, H, W], [-1, 1], RGB

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

[PIL.Image, ...]

Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be

Get mean and var for group norm

Get the index (e.g. 2) from the prediction (e.g. 'C')