src/about.py

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"""
## ABOUT
For now, the only competitive open language models capable of properly speaking Persian are the multilingual ones, Meta's Llama 3.1 being the prime example. 
There are only a few capable multilingual LLMs in Persian that derive their main knowledge from English. A Persian LLM is almost an imagination right now as there doesn't exist
that many models being expert in Persian in the first place.

Our goal is to provide a benchmark on diverse domains and tasks that provides insights on how much is the gap between the SOTA models right now in different settings.

We use our own framework to evaluate the models on the following benchmarks (TO BE RELEASED SOON)
### Tasks 
- <a href="https://arxiv.org/abs/1803.05457" target="_blank">  AI2 Reasoning Challenge </a> (25-shot) - a set of grade-school science questions.
- <a href="https://arxiv.org/abs/1905.07830" target="_blank">  HellaSwag </a> (10-shot) - a test of commonsense inference, which is easy for humans (~95%) but challenging for SOTA models.
- <a href="https://arxiv.org/abs/2009.03300" target="_blank">  MMLU </a>  (5-shot) - a test to measure a text model's multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more.
- <a href="https://arxiv.org/abs/2109.07958" target="_blank">  TruthfulQA </a> (0-shot) - a test to measure a model's propensity to reproduce falsehoods commonly found online. Note: TruthfulQA is technically a 6-shot task in the Harness because each example is prepended with 6 Q/A pairs, even in the 0-shot setting.
- <a href="https://arxiv.org/abs/1907.10641" target="_blank">  Winogrande </a> (5-shot) - an adversarial and difficult Winograd benchmark at scale, for commonsense reasoning.
- <a href="https://arxiv.org/abs/2110.14168" target="_blank">  GSM8k </a> (5-shot) - diverse grade school math word problems to measure a model's ability to solve multi-step mathematical reasoning problems.
For all these evaluations, a higher score is a better score.
We chose these benchmarks as they test a variety of reasoning and general knowledge across a wide variety of fields in 0-shot and few-shot settings.

## REPRODUCIBILITY
To reproduce our results, here are the commands you can run, using [this version](https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463) of the Eleuther AI Harness:
`python main.py --model=hf-causal-experimental --model_args="pretrained=<your_model>,use_accelerate=True,revision=<your_model_revision>"`
` --tasks=<task_list> --num_fewshot=<n_few_shot> --batch_size=1 --output_path=<output_path>`
```
python main.py --model=hf-causal-experimental \
    --model_args="pretrained=<your_model>,use_accelerate=True,revision=<your_model_revision>" \
    --tasks=<task_list> \
    --num_fewshot=<n_few_shot> \
    --batch_size=1 \
    --output_path=<output_path>
```
**Note:** We evaluate all models on a single node of 8 H100s, so the global batch size is 8 for each evaluation. If you don't use parallelism, adapt your batch size to fit.
*You can expect results to vary slightly for different batch sizes because of padding.*
The tasks and few shots parameters are:
- ARC: 25-shot, *arc-challenge* (`acc_norm`)
- HellaSwag: 10-shot, *hellaswag* (`acc_norm`)
- TruthfulQA: 0-shot, *truthfulqa-mc* (`mc2`)
- MMLU: 5-shot, *hendrycksTest-abstract_algebra,hendrycksTest-anatomy,hendrycksTest-astronomy,hendrycksTest-business_ethics,hendrycksTest-clinical_knowledge,hendrycksTest-college_biology,hendrycksTest-college_chemistry,hendrycksTest-college_computer_science,hendrycksTest-college_mathematics,hendrycksTest-college_medicine,hendrycksTest-college_physics,hendrycksTest-computer_security,hendrycksTest-conceptual_physics,hendrycksTest-econometrics,hendrycksTest-electrical_engineering,hendrycksTest-elementary_mathematics,hendrycksTest-formal_logic,hendrycksTest-global_facts,hendrycksTest-high_school_biology,hendrycksTest-high_school_chemistry,hendrycksTest-high_school_computer_science,hendrycksTest-high_school_european_history,hendrycksTest-high_school_geography,hendrycksTest-high_school_government_and_politics,hendrycksTest-high_school_macroeconomics,hendrycksTest-high_school_mathematics,hendrycksTest-high_school_microeconomics,hendrycksTest-high_school_physics,hendrycksTest-high_school_psychology,hendrycksTest-high_school_statistics,hendrycksTest-high_school_us_history,hendrycksTest-high_school_world_history,hendrycksTest-human_aging,hendrycksTest-human_sexuality,hendrycksTest-international_law,hendrycksTest-jurisprudence,hendrycksTest-logical_fallacies,hendrycksTest-machine_learning,hendrycksTest-management,hendrycksTest-marketing,hendrycksTest-medical_genetics,hendrycksTest-miscellaneous,hendrycksTest-moral_disputes,hendrycksTest-moral_scenarios,hendrycksTest-nutrition,hendrycksTest-philosophy,hendrycksTest-prehistory,hendrycksTest-professional_accounting,hendrycksTest-professional_law,hendrycksTest-professional_medicine,hendrycksTest-professional_psychology,hendrycksTest-public_relations,hendrycksTest-security_studies,hendrycksTest-sociology,hendrycksTest-us_foreign_policy,hendrycksTest-virology,hendrycksTest-world_religions* (average of all the results `acc`)
- Winogrande: 5-shot, *winogrande* (`acc`)
- GSM8k: 5-shot, *gsm8k* (`acc`)
Side note on the baseline scores: 
- for log-likelihood evaluation, we select the random baseline
- for GSM8K, we select the score obtained in the paper after finetuning a 6B model on the full GSM8K training set for 50 epochs
"""

EVALUATION_QUEUE_TEXT = """

## Important Notes

- 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 everyone reproduce the results.
- We only support models with **a causal language modeling head** for now.

## 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, AutoModelForCausalLM, AutoTokenizer
config = AutoConfig.from_pretrained("your model name", revision=revision)
model = AutoModelForCausalLM.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) 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 🤗

### 3) Fill up your model card
When we add extra information about models to the leaderboard, it will be automatically taken from the model card

### 4) 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).


## 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.

"""

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