from dataclasses import dataclass
from enum import Enum

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


class Tasks(Enum):
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard
    hallucination_rate = Task("hallucination_rate",
                            "hallucination_rate", "Hallucination Rate")
    accuracy = Task("factual_consistency_rate", "factual_consistency_rate", "Factual Consistency Rate")
    answer_rate = Task("answer_rate", "answer_rate", "Answer Rate")
    average_summary_length = Task("average_summary_length",
                                "average_summary_length", "Average Summary Length")
    # error_rate = Task("error_rate", "error_rate", "Error Rate")


# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">Hughes Hallucination Evaluation (H2EM) Model leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
This leaderboard evaluates how often an LLM introduces hallucinations when summarizing a document. 


"""

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

Using Vectara's H2EM (Hughes Hallucination Evaluation Model), we evaluate how often an LLM introduces hallucinations when summarizing a document. 

The model card for H2EM can be found [here](https://huggingface.co./vectara/hallucination_evaluation_model).
Given a document and a summary generated by an LLM, H2EM outputs a hallucination score between 0 and 1, where 0 means hallucination and 1 indicates no hallucination, or perfect factual consistency with the document. 

Our evaluation dataset is composed of 1006 documents from multiple public datasets, primarily [CNN/Daily Mail Corpus](https://huggingface.co./datasets/cnn_dailymail/viewer/1.0.0/test).
We generate summaries for each of these documents using submitted LLMs and compute hallucination scores for each pair of document and generated summary. (Check the prompt we used [here](https://huggingface.co./spaces/vectara/Hallucination-evaluation-leaderboard))

## Understand each metric
- Hallucination Rate: The percentage of summaries that have a hallucination score below 0.5
- Factual Consistency Rate: (1 - Hallucination Rate) * 100 (%)
- Answer Rate: The percentage of summaries that are non-empty. (This is a proxy for whether the model generates a summary at all)
- Average Summary Length: The average number of words in the generated summaries

## 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"""
"""