vlm_dataset_utils

Utility functions for getting samples and forward loop function for different vlm datasets.

Functions

get_vlm_dataset_dataloader

Get a dataloader with the dataset name and processor of the target model.

get_supported_vlm_datasets

Retrieves a list of vlm datasets supported.

get_supported_vlm_datasets()

Retrieves a list of vlm datasets supported.

Returns:

A list of strings, where each string is the name of a supported dataset.

Return type:

list[str]

Example usage:

from modelopt.torch.utils import get_supported_vlm_datasets

print("Supported datasets:", get_supported_vlm_datasets())
get_vlm_dataset_dataloader(dataset_name='scienceqa', processor=None, batch_size=1, num_samples=512)

Get a dataloader with the dataset name and processor of the target model.

Parameters:
  • dataset_name (str) – Name of the dataset to load.

  • processor (MllamaImageProcessor) – Processor used for encoding images and text data.

  • batch_size (int) – Batch size of the returned dataloader.

  • num_samples (int) – Number of samples from the dataset.

Returns:

An instance of dataloader.

Return type:

DataLoader