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
# ---------------------------------------------------



# Add an ID to the h1 tag for easy CSS targeting
TITLE = """<h1 id="main-leaderboard-title" align="center">🏆 MLE-Dojo Benchmark Leaderboard</h1>"""

# Use standard Markdown or wrap in a div with a class
INTRODUCTION_TEXT = """
<div id="intro" class="introduction-section">
    <p>MLE-Dojo is a Gym-style framework for systematically training, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows.</p>
</div>
"""
# INTRODUCTION_TEXT = """
# <div id="intro" class="introduction-section">
#     <p>MLE-Dojo is a Gym-style framework for systematically training, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows.</p>
# </div>

# <p align="center" style="font-family:'Segoe UI', Roboto, sans-serif; font-weight:bold; text-transform:uppercase;">
#   <a href="https://arxiv.org/abs/1706.03762">
#     <img src="https://img.shields.io/badge/Arxiv-1706.03762-000000.svg?style=flat-square&logo=arxiv&logoColor=%23FFD700&labelColor=000000" height="28">
#   </a>
#   &nbsp;&nbsp;&nbsp;
#   <a href="https://mle-dojo.github.io/MLE-Dojo-page/">
#     <img src="https://img.shields.io/badge/Project%20Website-%20-000000.svg?style=flat-square&logo=Google-Chrome&logoColor=%23FFD700&labelColor=000000" height="28">
#   </a>
#   &nbsp;&nbsp;&nbsp;
#   <a href="https://github.com/MLE-Dojo/MLE-Dojo">
#     <img src="https://img.shields.io/badge/Code-000000.svg?style=flat-square&logo=github&logoColor=%23FFD700&labelColor=000000" height="28">
#   </a>
# </p>
# """

# ... (rest of your about.py content) ...
LLM_BENCHMARKS_TEXT = """
## MLE-Dojo
MLE-Dojo is a Gym-style framework for systematically training, evaluating, and improving autonomous large language model (LLM) agents in 
iterative machine learning engineering (MLE) workflows. Built upon 200+ real-world Kaggle challenges. MLE-Dojo covers diverse, 
open-ended MLE tasks carefully curated to reflect realistic Machine Learning Engineering scenarios such as data processing, 
architecture search, hyperparameter tuning, and code debugging, etc. MLE-Dojo's fully executable environment and flexible 
interface support comprehensive agent training via both supervised fine-tuning and reinforcement learning, facilitating 
iterative experimentation, realistic data sampling, and real-time outcome verification.
## New Updates
We actively maintain this as a long-term real-time leaderboard with updated models and evaluation tasks to foster community-driven innovation.
"""

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 the paper."
CITATION_BUTTON_TEXT = r"""
@misc{qiang2025mledojointeractiveenvironmentsempowering,
      title={MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering}, 
      author={Rushi Qiang and Yuchen Zhuang and Yinghao Li and Dingu Sagar V K and Rongzhi Zhang and Changhao Li and Ian Shu-Hei Wong and Sherry Yang and Percy Liang and Chao Zhang and Bo Dai},
      year={2025},
      eprint={2505.07782},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2505.07782}, 
}
"""