src/display/about.py

from dataclasses import dataclass
from enum import Enum

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


# Init: to update with your specific keys
class Tasks(Enum):
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
    task0 = Task("logiqa", "delta_abs", "LogiQA Δ")
    task1 = Task("logiqa2", "delta_abs", "LogiQA2 Δ")
    task2 = Task("lsat-ar", "delta_abs", "LSAT-ar Δ")
    task3 = Task("lsat-lr", "delta_abs", "LSAT-lr Δ")
    task4 = Task("lsat-rc", "delta_abs", "LSAT-rc Δ")

#METRICS = list(set([task.value.metric for task in Tasks]))



# Your leaderboard name
TITLE = """<h1 align="center" id="space-title"><code>/\/</code> &nbsp; Open CoT Leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
Intro text
"""

# 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 with `vLLM`:
```python
from vllm import LLM, SamplingParams
prompts = [
    "Hello, my name is",
    "The president of the United States is",
    "The capital of France is",
    "The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="<USER>/<MODEL>")
outputs = llm.generate(prompts, sampling_params)
```
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!

### 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

## Your model is stuck in the pending queue?

We're populating the Open CoT Leaderboard step by step. The idea is to grow a diverse and informative sample of the LLM space. Plus, with limited compute, we're currently prioritizing models that are popular, promising, and relatively small.

"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
"""