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 
    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">Meta-Reasoning leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
Welcome to the meta-reasoning leaderboard. This space holds the results from our two meta-reasoning papers "Mr-Ben: A Comprehensive Meta-Reasoning Benchmark for Large Language Models" and "MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation". 
For both datasets, we have provided a demo evaluate script for you to try out benchmark in at most two commands. We encourage everyone to try out our benchmark in the SOTA models and return its results to us.
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works
This meta-reasoning paradigm casts LLMs in the role of a teacher, where they assess the reasoning process by evaluating its correctness, analyzing errors, and providing corrections.

## Reproducibility
To reproduce our results, please check out our demo scripts [Mr-Ben](https://github.com/dvlab-research/Mr-Ben?tab=readme-ov-file#how-to-evaluate-on-mr-ben) and [MR-GSM8K](https://github.com/dvlab-research/MR-GSM8K?tab=readme-ov-file#evaluate-on-mr-gsm8k).
All we need is an access to your evaluated model and a proxy scoring model say GPT-4-Turbo. Then you should be able to reproduce our results directly out of the box.
"""

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 = "If you find our benchmarks helpful, please copy the following snippet to cite our works"
CITATION_BUTTON_TEXT = r"""
@article{zeng2024mrben,
  author       = {Zhongshen Zeng and Yinhong Liu and Yingjia Wan and Jingyao Li and Pengguang Chen and Jianbo Dai and Yuxuan Yao and Rongwu Xu and Zehan Qi and Wanru Zhao and Linling Shen and Jianqiao Lu and Haochen Tan and Yukang Chen and Hao Zhang and Zhan Shi and Bailin Wang and Zhijiang Guo and Jiaya Jia},
  title        = {MR-BEN: A Comprehensive Meta-Reasoning Benchmark for Large Language Models},
  journal      = {CoRR},
  volume       = {abs/2406.13975},
  year         = {2024},
  url          = {https://arxiv.org/abs/2406.13975},
  eprinttype    = {arXiv},
  eprint       = {2406.13975}
}


@article{DBLP:journals/corr/abs-2312-17080,
  author       = {Zhongshen Zeng and Pengguang Chen and Shu Liu and Haiyun Jiang and Jiaya Jia},
  title        = {MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation},
  journal      = {CoRR},
  volume       = {abs/2312.17080},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2312.17080},
  doi          = {10.48550/ARXIV.2312.17080},
  eprinttype    = {arXiv},
  eprint       = {2312.17080},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2312-17080.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

"""