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("task_name1", "metric_name", "First task")
    # task1 = Task("task_name2", "metric_name", "Second task")

    task0 = Task("finance_bench", "accuracy", "FinanceBench")
    task1 = Task("legal_confidentiality", "accuracy", "Legal Confidentiality")
    task2 = Task("writing-prompts", "coherence", "Writing Prompts")
    task3 = Task("customer-support", "engagement", "Customer Support Dialogue")
    task4 = Task("toxic-prompts", "toxicity", "Toxic Prompts")
    task5 = Task("enterprise-pii", "accuracy", "Enterprise PII")


# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">Patronus AI leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
This leaderboard evaluates the performance of models on real-world enterprise use cases. 
"""

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

## Tasks
1. FinanceBench: The task measures the ability to answer financial questions given the context. 

2. Legal Confidentiality: The task measures the ability of LLMs to reason over legal causes. The model is prompted 
to return yes/no as an answer to the question. 

3. Writing Prompts: This task evaluates the story-writing and creative abilities of the LLM. 

4. Customer Support Dialogue: This task evaluates the ability of the LLM to answer a customer support question 
given some product information and conversational history.

5. Toxic Prompts: This task evaluates the safety of the model by using prompts that can elicit harmful information 
from LLMs.

6. Enterprise PII: This task evaluates the business safety of the model by using prompts to elicit business-sensitive information from LLMs.

## Reproducibility
All of our datasets are closed-source. We provide a validation set with 5 examples for each of the tasks.


"""

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"""
"""