from dataclasses import dataclass
from enum import Enum
@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
task0 = Task("mmlu_it", "acc", "MMLU_IT")
task1 = Task("arc_it", "acc_norm", "ARC_IT")
task2 = Task("hellaswag_it", "acc_norm", "HELLASWAG_IT")
NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------
# Your leaderboard name
TITLE = """🚀 Classifica generale degli LLM italiani 🚀
"""
# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
Benvenuti nella pagina della Open ITA LLM Leaderboard!
In questa dashboard potrete trovare tutti i risultati delle performance dei Large Language Models in lingua italiana sui principali test di valutazione, effettuati grazie alla [Eleuther AI Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness)
Maggiori informazioni sono disponibili nella sezione "About".
La classifica è completamente open source e chiunque può contribuire aggiungendo il proprio modello tramite l'apposita sezione "Submit".
Le valutazioni sono automatizzate e i risultati saranno disponibili entro un paio d'ore. Questo è reso possibile grazie alla GPU A100 di [Seeweb](https://www.seeweb.it/prodotti/cloud-server-gpu).
Per gli LLM di dimensioni superiori a 35B, si prega di inviare la richiesta tramite questo [form](https://forms.gle/Gc9Dfu52xSBhQPpAA).
Se avete idee, miglioramenti o suggerimenti, non esitate a [contattarmi](https://www.linkedin.com/in/samuele-colombo-ml/) oppure trovatemi sul [server Discord della community](https://discord.gg/kc97Zwc4ze).
"""
# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## Come funziona
Valutiamo i modelli tramite Eleuther AI Language Model Evaluation Harness , il framework più utilizzato dalla community internazionale per l'evaluation dei modelli
Nella classifica troverete i dataset di benchmark più famosi, adatti alla lingua italiana. I task sono:
- hellaswag_it
- arc_it
- m_mmlu_it (5 shots)
Per tutti questi task, a un punteggio migliore corrisponde una performance maggiore
## Reproducibility
Per riprodurre i risultati scaricate la Eleuther AI Language Model Evaluation Harness ed eseguite:
* lm-eval --model hf --model_args pretrained= --tasks hellaswag_it,arc_it --device cuda:0 --batch_size auto:2;
* lm-eval --model hf --model_args pretrained=, --tasks m_mmlu_it --num_fewshot 5 --device cuda:0 --batch_size auto:2
"""
EVALUATION_QUEUE_TEXT = """
## PLEASE SUBMIT ONLY LLMS SPECIALIZED FOR ITALIAN TASKS OR BASE MODELS FROM MAJOR LABS (E.G., META, MISTRAL) THAT PERFORM VERY WELL ON ITALIAN DESPITE NOT BEING SPECIFICALLY TRAINED FOR IT WILL BE ACCEPTED.
### 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"""
Paper coming soon!
Pls dateci credits se usate i nostri benchmarks :)
"""