|
from dataclasses import dataclass |
|
from enum import Enum |
|
|
|
@dataclass |
|
class Task: |
|
benchmark: str |
|
metric: str |
|
col_name: str |
|
|
|
|
|
|
|
|
|
class Tasks(Enum): |
|
|
|
task0 = Task("anli_r1", "acc", "ANLI") |
|
task1 = Task("logiqa", "acc_norm", "LogiQA") |
|
|
|
NUM_FEWSHOT = 0 |
|
|
|
|
|
|
|
|
|
|
|
TITLE = """<h1 align="center" id="space-title">Align-Anything</h1>""" |
|
|
|
|
|
|
|
|
|
INTRODUCTION_TEXT = """ |
|
# Align-Anything: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models |
|
We present Align-Anything, a Massive Multimodal Interleaved understanding Evaluation benchmark, designed for Large Vision-Language Models (LVLMs). Align-Anything offers a robust framework for evaluating the interleaved comprehension and generation capabilities of LVLMs across diverse fields, supported by reliable automated metrics. |
|
[Website](https://Align-Anything-bench.github.io) | [Code](https://github.com/Lillianwei-h/Align-Anything) | [Dataset](https://huggingface.co/datasets/Align-Anything/Align-Anything) | [Results](https://huggingface.co/spaces/Align-Anything/Leaderboard) | [Evaluation Model](https://huggingface.co/Align-Anything/Align-Anything-Score) | [Paper](https://arxiv.org/abs/2410.10139) |
|
""" |
|
|
|
|
|
LLM_BENCHMARKS_TEXT = f""" |
|
""" |
|
|
|
EVALUATION_QUEUE_TEXT = """ |
|
""" |
|
|
|
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results" |
|
CITATION_BUTTON_TEXT = """ |
|
@article{xia2024Align-Anything, |
|
title={Align-Anything: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models}, |
|
author={Xia, Peng and Han, Siwei and Qiu, Shi and Zhou, Yiyang and Wang, Zhaoyang and Zheng, Wenhao and Chen, Zhaorun and Cui, Chenhang and Ding, Mingyu and Li, Linjie and Wang, Lijuan and Yao, Huaxiu}, |
|
journal={arXiv preprint arXiv:2410.10139}, |
|
year={2024} |
|
} |
|
""" |
|
|
|
|
|
ABOUT_TEXT = """ |
|
""" |