Rearrange 1D padded tensor into a 2D tensor with zeros uniformly distributed. Thanks to DeepSeek-R1. Args:

This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring o

This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring o

Check if the current Python environment contains all the libraries that are imported in a file.

Retrieve pipeline class that inherits from `DiffusionPipeline`. Note that there has to be exactly one class inheriting from `DiffusionPipelin

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

Returns the activation function corresponding to `activation`

Prepares Downloads a module from a local folder or a distant repo and returns its path inside the cached Transformers module. Args:

Import a module on the cache directory for modules and extract a class from it.

Return a list of indices so that each slice of `batch_size` consecutive indices correspond to elements of similar lengths. To do this, the in

Calculate the 3D rope index based on image and video's temporal, height and width in LLM. Explanation: Each embedding se

Calculate the 3D rope index based on image and video's temporal, height and width in LLM. Explanation: Each embedding se

Calculate the 3D rope index based on image and video's temporal, height and width in LLM. Explanation: Each embedding se

Calculate the 3D rope index based on image and video's temporal, height and width in LLM. Explanation: Each embedding se

Creates the cache directory for modules with an init, and adds it to the Python path.

Accepts images in list or nested list format, and makes a list of images for preprocessing. Args: images (`Union[List[List[ImageInpu

Make dataset and collator for supervised fine-tuning.

Parse command-line arguments.

Run inference on ActivityNet QA DataSet using the Video-ChatGPT model. Args: args: Command-line arguments.

Rescales the image so that the following conditions are met: 1. Both dimensions (height and width) are divisible by 'factor'. 2. The total n

Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64.

Split a list into n (roughly) equal-sized chunks

Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments

Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments

Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments

Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments