from dataclasses import dataclass
from enum import Enum
@dataclass
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
# For MMLongBench-Doc (https://arxiv.org/abs/2407.01523), we use ACC as the main metric
task0 = Task("mmlongbench_doc", "acc", "ACC")
NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------
# Your leaderboard name
TITLE = """"""
# Links and conference info
LINKS_AND_INFO = """
"""
# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
📚 [MMLongBench-Doc](https://arxiv.org/abs/2407.01523) is a long-context, multimodal document understanding benchmark designed to evaluate the performance of large multimodal models on complex document understanding tasks.
📊 This leaderboard tracks the performance of various models on the [MMLongBench-Doc](https://arxiv.org/abs/2407.01523) benchmark, focusing on their ability to understand and process long documents with both text and visual elements.
🔧 You can use the official [GitHub repo](https://github.com/mayubo2333/MMLongBench-Doc) or [VLMEvalKit](https://github.com/open-compass/VLMEvalKit) to evaluate your model on [MMLongBench-Doc](https://arxiv.org/abs/2407.01523). We provide the [official evaluation results](https://huggingface.co/datasets/OpenIXCLab/mmlongbench-doc-results) of GPT-4.1 and GPT-4o.
📝 To add your own model to the leaderboard, please send an Email to yubo001@e.ntu.edu.sg or zangyuhang@pjlab.org.cn then we will help with the evaluation and updating the leaderboard.
"""
# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works
[MMLongBench-Doc](https://arxiv.org/abs/2407.01523) evaluates multimodal models on their ability to understand long documents containing both text and visual elements. The benchmark includes various document understanding tasks that require models to process and reason over extended contexts.
## Evaluation Metrics
- **ACC (Accuracy)**: The primary metric measuring the overall accuracy of model predictions on document understanding tasks.
- **Parameters**: Model size in billions of parameters
- **Open Source**: Whether the model weights are publicly available
## Reproducibility
To reproduce our results, please refer to the official [MMLongBench-Doc](https://arxiv.org/abs/2407.01523) repository for evaluation scripts and detailed instructions.
"""
EVALUATION_QUEUE_TEXT = """
## Some good practices before submitting a model
### 1) Make sure you can load your model and tokenizer using AutoClasses:
```python
from transformers import AutoConfig, AutoModel, AutoTokenizer
config = AutoConfig.from_pretrained("your model name", revision=revision)
model = AutoModel.from_pretrained("your model name", revision=revision)
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
```
If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.
Note: make sure your model is public!
Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!
### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!
### 3) Make sure your model has an open license!
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗
### 4) Fill up your model card
When we add extra information about models to the leaderboard, it will be automatically taken from the model card
## In case of model failure
If your model is displayed in the `FAILED` category, its execution stopped.
Make sure you have followed the above steps first.
If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
"""
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""@inproceedings{ma2024mmlongbenchdoc,
title={{MMLONGBENCH}-{DOC}: Benchmarking Long-context Document Understanding with Visualizations},
author={Yubo Ma and Yuhang Zang and Liangyu Chen and Meiqi Chen and Yizhu Jiao and Xinze Li and Xinyuan Lu and Ziyu Liu and Yan Ma and Xiaoyi Dong and Pan Zhang and Liangming Pan and Yu-Gang Jiang and Jiaqi Wang and Yixin Cao and Aixin Sun},
booktitle={NeurIPS Datasets and Benchmarks Track},
year={2024},
url={https://openreview.net/forum?id=loJM1acwzf}
}"""