Copy the master parameter data back into the model parameters.

Copy the gradients from the model parameters into the master parameters from make_master_params().

Copied from: https://github.com/openai/baselines/blob/ea25b9e8b234e6ee1bca43083f8f3cf974143998/baselines/common/mpi_util.py#L110 Perform a we

Generate samples from the model and yield intermediate samples from each timestep of diffusion. Arguments are the same as p_

Pad sequences and convert them to numpy.

Generate with fixed prompt pretrained

Sample x_{t-1} from the model using Pseudo Linear Multistep. Same usage as p_sample().

Use PLMS to sample from the model and yield intermediate samples from each timestep of PLMS. Same usage as p_sample_loop_pro

Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer}

构建伪标签摘要数据集

Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of dif

This function is copy of `random_spans_helper <https://github.com/google-research/text-to-text-transfer-transformer/ blob/84f8bcc14b5f2c03de51

Recursively set attributes on a pytorch module or an iterable of modules. If an assert_type is provided, it will assert that the type of the

Register a new model in this mapping.

sample from posterior Gaussian family Args: mu: Tensor Mean of gaussian distribution with shape (batch, nz) logvar: Te

Simple GPU memory report.

Initialize the transition parameters. The parameters will be initialized randomly from a uniform distribution between -0.1 and 0.1.

Init method based on N(0, sigma/sqrt(2*num_layers).

Init method based on N(0, sigma/sqrt(2*num_layers).

Init method based on N(0, sigma/sqrt(2*num_layers).

Shift input ids one token to the right.

Shift input ids one token to the right.

Shift input ids one token to the right.

Shift input ids one token to the right.