from dataclasses import dataclass
from enum import Enum
from src.envs import REPO_ID


@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("PeKA", "acc", "PeKA*")
    task2 = Task("PersBETS", "acc", "PersBETS*")
    task3 = Task("khayyam_challenge", "acc", "Khayyam Challenge")
    task4 = Task("parsinlu_mc", "acc", "ParsiNLU MCQA")
    task5 = Task("parsinlu_nli", "acc", "ParsiNLU NLI")
    task6 = Task("parsinlu_qqp", "acc", "ParsiNLU QQP")
    # task7 = Task("persian_ARC", "acc", "Persian ARC")

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



# Your leaderboard name
TITLE = f"""
<img src="https://huggingface.co/spaces/{REPO_ID}/resolve/main/banner_green.png" style="width:70%;display:block;margin-left:auto;margin-right:auto">
"""


# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
Persian LLM Leaderboard is designed to be a challenging benchmark and provide a reliable evaluation of LLMs in Persian Language. 

Note: This is a demo version of the leaderboard. Two new benchmarks are introduced: *PeKA* and *PersBETS*, challenging the native knowledge of the models along with 
linguistic skills and their level of bias, ethics, and trustworthiness. **These datasets are not yet public, but they will be uploaded onto huggingface along with a detailed paper
explaining the data and performance of relevent models.**

Note: **We plan to release an evaluation framework soon in which the details and methods of evaluation are specified.**
"""

# 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 = """

Right now, the models added **are not automatically evaluated**. We may support automatic evaluation in the future on our own clusters.
An evaluation framework will be available in the future to help reproduce the results.

## Don't forget to read the FAQ and the About tabs for more information!

## First steps 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!

### 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.

### 5) Select the correct precision
Not all models are converted properly from `float16` to `bfloat16`, and selecting the wrong precision can sometimes cause evaluation error (as loading a `bf16` model in `fp16` can sometimes generate NaNs, depending on the weight range).


"""

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