Spaces:
Running
Running
| from dataclasses import dataclass | |
| from enum import Enum | |
| class Task: | |
| benchmark: str | |
| metric: str | |
| col_name: str | |
| # Select your tasks here | |
| # --------------------------------------------------- | |
| class Tasks(Enum): | |
| # task_key in the json file, metric_key in the json file, name to display in the leaderboard | |
| task0 = Task("anli_r1", "acc", "ANLI") | |
| task1 = Task("logiqa", "acc_norm", "LogiQA") | |
| NUM_FEWSHOT = 0 # Change with your few shot | |
| # --------------------------------------------------- | |
| # Your leaderboard name | |
| TITLE = """<h1 align="center" id="space-title">MMIE</h1>""" | |
| # MJB_LOGO = '<img src="" alt="Logo" style="width: 30%; display: block; margin: auto;">' | |
| # What does your leaderboard evaluate? | |
| INTRODUCTION_TEXT = """ | |
| # MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models | |
| [Website](https://github.com/richard-peng-xia/MMIE) | [Code](https://github.com/richard-peng-xia/MMIE) | [Dataset](https://huggingface.co/datasets/MMIE/MMIE) | [Results](https://huggingface.co/spaces/MMIE/Leaderboard) | [Eval Model](https://huggingface.co/MMIE/MMIE-Eval) | [Paper]() | |
| """ | |
| # Which evaluations are you running? how can people reproduce what you have? | |
| LLM_BENCHMARKS_TEXT = f""" | |
| """ | |
| EVALUATION_QUEUE_TEXT = """ | |
| """ | |
| CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results" | |
| CITATION_BUTTON_TEXT = r""" | |
| """ | |
| ABOUT_TEXT = """ | |
| """ | |