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("toxicity", "aggregated-results", "Non-toxicity")
    task1 = Task("stereotype", "aggregated-results", "Non-Stereotype")
    task2 = Task("adv", "aggregated-results", "AdvGLUE++")
    task3 = Task("ood", "aggregated-results", "OoD")
    task4 = Task("adv_demo", "aggregated-results", "Adv Demo")
    task5 = Task("privacy", "aggregated-results", "Privacy")
    task6 = Task("ethics", "aggregated-results", "Ethics")
    task7 = Task("fairness", "aggregated-results", "Fairness")


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

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """The Safe LLM Leaderboard aims to provide a unified evaluation for LLM safety and help 
researchers and practitioners better understand the capabilities, limitations, and potential risks of LLMs. Submit a 
model for evaluation on the “Submit” page! The leaderboard is generated based on the trustworthiness evaluation 
platform [DecodingTrust](https://decodingtrust.github.io/)."""

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

As LLMs have demonstrated impressive capabilities and are being deployed in 
high-stakes domains such as healthcare, transportation, and finance, understanding the safety, limitations, 
and potential risks of LLMs is crucial.

## How it works

This leaderboard is powered by the DecodingTrust platform, which provides comprehensive safety and trustworthiness 
evaluation for LLMs. More details about the paper, which has won the Outstanding Paper award at NeurIPs’23, 
and the platform can be found here.

DecodingTrust aims to provide comprehensive risk and trustworthiness assessment for LLMs. Currently, it includes the 
following eight primary perspectives of trustworthiness, including:
+ Toxicity
+ Stereotype and bias
+ Adversarial robustness
+ Out-of-Distribution Robustness
+ Privacy
+ Robustness to Adversarial Demonstrations
+ Machine Ethics
+ Fairness

We normalize the evaluation score of each perspective between 0-100, which means the higher the better.

Examples of these vulnerabilities are shown below.
![DecodingTrust Overview](https://decodingtrust.github.io/overview.png)


We normalize the score of each perspective as 0-100, and these scores are the higher the better.

## Reproducibility
To reproduce our results, checkout https://github.com/AI-secure/DecodingTrust

"""

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"""
@article{wang2023decodingtrust,
  title={DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models},
  author={Wang, Boxin and Chen, Weixin and Pei, Hengzhi and Xie, Chulin and Kang, Mintong and Zhang, Chenhui and Xu, Chejian and Xiong, Zidi and Dutta, Ritik and Schaeffer, Rylan and others},
  booktitle={Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
  year={2023}
}
"""