📄 Energy And Power¶

MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence (AGI).

Tags: language:['en'], license:apache-2.0, size_categories:['10K<n<100K'], task_categories:['question-answering', 'visual-question-answering', 'multiple-choice'], category:dataset

cards.mmmu.energy_and_power

TaskCard(
    loader=LoadHF(
        path="MMMU/MMMU",
        name="Energy_and_Power",
        data_classification_policy=[
            "public",
        ],
    ),
    preprocess_steps=[
        RenameSplits(
            mapper={
                "dev": "train",
                "validation": "test",
            },
        ),
        ListFieldValues(
            fields=[
                "image_1",
                "image_2",
                "image_3",
                "image_4",
                "image_5",
                "image_6",
                "image_7",
            ],
            to_field="media/images",
        ),
        Filter(
            field="media/images",
            values=[
                None,
            ],
        ),
        MapReplace(
            field_to_field={
                "question": "question",
                "options": "choices",
            },
            mapping={
                "<image 1>": "<img src="media/images/0">",
                "<image 2>": "<img src="media/images/1">",
                "<image 3>": "<img src="media/images/2">",
                "<image 4>": "<img src="media/images/3">",
                "<image 5>": "<img src="media/images/4">",
                "<image 6>": "<img src="media/images/5">",
                "<image 7>": "<img src="media/images/6">",
            },
        ),
        LiteralEval(
            field="choices",
        ),
        Lower(
            field="subfield",
            to_field="topic",
        ),
        MapValues(
            field="answer",
            mapping={
                "A": 0,
                "B": 1,
                "C": 2,
                "D": 3,
                "E": 4,
                "?": None,
            },
        ),
    ],
    task="tasks.qa.multiple_choice.with_topic",
    templates="templates.qa.multiple_choice.with_topic.all",
)

[source]

from unitxt.collections_operators import Filter
from unitxt.loaders import LoadHF
from unitxt.operators import ListFieldValues, MapValues
from unitxt.processors import LiteralEval, Lower
from unitxt.splitters import RenameSplits
from unitxt.string_operators import MapReplace

Explanation about TaskCard¶

TaskCard delineates the phases in transforming the source dataset into model input, and specifies the metrics for evaluation of model output.

Args:

loader:
specifies the source address and the loading operator that can access that source and transform it into a unitxt multistream.

preprocess_steps:
list of unitxt operators to process the data source into model input.

task:
specifies the fields (of the already (pre)processed instance) making the inputs, the fields making the outputs, and the metrics to be used for evaluating the model output.

templates:
format strings to be applied on the input fields (specified by the task) and the output fields. The template also carries the instructions and the list of postprocessing steps, to be applied to the model output.

Explanation about LoadHF¶

Loads datasets from the HuggingFace Hub.

It supports loading with or without streaming, and it can filter datasets upon loading.
Args:

path:
The path or identifier of the dataset on the HuggingFace Hub.

name:
An optional dataset name.

data_dir:
Optional directory to store downloaded data.

split:
Optional specification of which split to load.

data_files:
Optional specification of particular data files to load. When you provide a list of data_files to Hugging Face’s load_dataset function without explicitly specifying the split argument, these files are automatically placed into the train split.

revision:
Optional. The revision of the dataset. Often the commit id. Use in case you want to set the dataset version.

streaming (bool):
indicating if streaming should be used.

filtering_lambda (str, optional):
A lambda function for filtering the data after loading.

num_proc (int, optional):
Specifies the number of processes to use for parallel dataset loading.

Example:
Loading glue’s mrpc dataset
load_hf = LoadHF(path='glue', name='mrpc')

Explanation about ListFieldValues¶

Concatenates values of multiple fields into a list, and assigns it to a new field.

References: templates.qa.multiple_choice.with_topic.all, tasks.qa.multiple_choice.with_topic