src/about.py

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 
    cmmmu = Task("cmmmu", "acc", "CMMMU")
    cmmu = Task("cmmu", "acc", "CMMU")
    cv_bench = Task("cv_bench", "acc", "CV_Bench")
    hallusion_bench = Task("hallusion_bench", "acc", "Hallusion_Bench")
    mmmu = Task("mmmu", "acc", "MMMU")
    mmmu_pro_standard = Task("mmmu_pro_standard", "acc", "MMMU_Pro_Standard")
    mmmu_pro_vision = Task("mmmu_pro_vision", "acc", "MMMU_Pro_Vision")
    ocrbench = Task("ocrbench", "acc", "OCRBench")
    math_vision = Task("math_vision", "acc", "Math_Vision")
    ciibench = Task("ciibench", "acc", "CIIBench")

NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------



# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">FlagEval-VLM Leaderboard</h1>"""

# What does your leaderboard evaluate?

INTRODUCTION_TEXT = """
FlagEval-VLM Leaderboard旨在跟踪、排名和评估VLM。本排行榜由FlagEval平台提供相应算力和运行环境。
评估数据集是全部都是中文数据集以评估中文能力如需查看详情信息，请查阅‘关于’页面。
如需对模型进行更全面的评测，可以登录 [FlagEval](https://flageval.baai.ac.cn/api/users/providers/hf)平台，体验更加完善的模型评测功能。

The FlagEval-VLM Leaderboard aims to track, rank, and evaluate VLMs. This leaderboard is powered by the FlagEval platform, providing corresponding computational resources and runtime environment.
The evaluation dataset consists entirely of Chinese data to assess Chinese language proficiency. For more detailed information, please refer to the 'About' page.
For a more comprehensive evaluation of the model, you can log in to the [FlagEval](https://flageval.baai.ac.cn/) to experience more refined model evaluation functionalities

"""
# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works

## Reproducibility
To reproduce our results, here is the commands you can run:

"""

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"""
"""