Prepare optimizer and schedule

Converts a sequence of ids in wordpiece tokens using the vocab.

Convert primitive modules to float16.

Convert primitive modules to float32, undoing convert_module_to_f16().

Convert the torso of the model to float16.

Convert the torso of the model to float16.

Convert the torso of the model to float32.

Convert the torso of the model to float32.

Converts `text` to Unicode (if it's not already), assuming utf-8 input.

Converts a sequence of tokens into ids using the vocab.

Converts a sequence of tokens (string) in a single string.

Converts a sequence of tokens (string) in a single string.

Create a ScheduleSampler from a library of pre-defined samplers. :param name: the name of the sampler. :param diffusion: the diffusion o

Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding symbols are ignored. This is modifi

We are provided embeddings directly. We cannot infer which are padded so just generate sequential position ids. Args: in

Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make use of token type ids

中文分句，默认？、。、！、省略号分句，考虑双引号包裹的句子 采用分割替换的方式

Sample x_{t+1} from the model using DDIM reverse ODE.

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

Generate samples from the model using DDIM. Same usage as p_sample_loop().

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

This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this

测试推理速度

Generate with fixed prompt of deduction

Set the groups to none.

Write all of the diagnostics from the current iteration