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("caselawqa", "exact_match,default", "CaselawQA")
    task1 = Task("caselawqa_sc", "exact_match,default", "Supreme Court")
    task2 = Task("caselawqa_songer", "exact_match,default", "Courts of Appeals")
    
NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------


# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">CaselawQA leaderboard (WIP)</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
CaselawQA is a benchmark comprising legal classification tasks derived from the Supreme Court and Songer Court of Appeals legal databases.
From a technical machine learning perspective, these tasks provide highly non-trivial classification problems where even the best models leave much room for improvement. 
From a substantive legal perspective, efficient solutions to such classification problems have rich and important applications in legal research.
"""

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

CaselawQA is a benchmark comprising legal classification tasks derived from the Supreme Court and Songer Court of Appeals legal databases.
The majority of its 10,000 questions are multiple-choice, with 5,000 sourced from each database. 
The questions are randomly selected from the test sets of the [Lawma tasks](https://huggingface.co/datasets/ricdomolm/lawma-tasks).


From a technical machine learning perspective, these tasks provide highly non-trivial classification problems where even the best models leave much room for improvement. 
From a substantive legal perspective, efficient solutions to such classification problems have rich and important applications in legal research.


You can find more information in the [Lawma arXiv preprint](https://arxiv.org/abs/2407.16615) and [GitHub repository](https://github.com/socialfoundations/lawma).

## Reproducibility

With evaluate CaselawQA using [this](https://github.com/socialfoundations/lm-evaluation-harness/tree/caselawqa) LM Eval Harness implementation:

```bash
lm_eval --model hf --model_args "pretrained=<your_model>,dtype=bfloat16" --tasks caselawqa --output_path=<output_path>
"""

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.

### 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) 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"""
@misc{dominguezolmedo2024lawma,
      title={Lawma: The Power of Specialization for Legal Tasks}, 
      author={Ricardo Dominguez-Olmedo and Vedant Nanda and Rediet Abebe and Stefan Bechtold and Christoph Engel and Jens Frankenreiter and Krishna Gummadi and Moritz Hardt and Michael Livermore},
      year={2024},
      eprint={2407.16615},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2407.16615}, 
}
"""