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 
    task1 = Task("community|pr-fouras|0", "pr-fouras-qem", "Pr-Fouras")
    task2 = Task("community|kangourou-to|0", "norm_acc", "Kangourou-TO")
    task3 = Task("community|sornette|0", "norm_acc", "Sornette")

@dataclass
class MixTasks:
    benchmark: str
    metric: str
    col_name: str

# Select your sub tasks here for Mix-fr
# ---------------------------------------------------
class MixTasks(Enum):
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
    task1 = Task("community|ifeval-fr|0", "norm_acc", "IFEval-Fr")
    task2 = Task("community|gpqa-fr|0", "norm_acc", "GPQA-Fr")
    task3 = Task("community|bac-fr|0", "bac-fr-qem", "Bac-Fr")
    

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



# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">
 <img src="https://www.deepmama.com/images/deepmamaFRLLMleaderboard.png" alt="FIDLE Evaluator" width="50%">
 </h1> 
"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
-------------------------
# LLM-FR Leaderboard 🏆

This leaderboard evaluates intelligence modeling in the French language. It is not intended to serve as a reference for LLM evaluations. It is provided for informational and educational purposes only. Please consult other, more official leaderboards for authoritative assessments.

**Note: The assessments have been adapted to the Reasoning Language Model**: all *tasks* are in generative mode, with no limit on token generation.
* **Pr-Fouras** : "Père Fouras"'s Riddles (ex : [fan site](https://www.fan-fortboyard.fr/pages/fanzone/enigmes-du-pere-fouras/))
* **Kangourou-TO** : MATH Quizzes [Kangourou](www.mathkang.org). *Text Only* : Only questions without figures.
* **Sornette** : Classification of texts (GORAFI, wikipedia, le saviez-vous, ...) into 4 categories - `burlesque et fantaisiste`, `ludique et didactique`, `insidieux et mensonger`, `moral et accablant`
* **Mix-Fr** : 🍲 Mixture of public datasets translated in french

**Model Types**:
* 🪨 - Base, Pretrained, Foundation Model
* 💬 - Chat Model (Instruct, RLHF, DPO, ...)
* 💅🏻 - Fine-tuned Model
* 🤔 - Reasoning Model
"""

# 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"""
"""