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("pinocchio_it_generale", "acc", "generale") task1 = Task("pinocchio_it_logica", "acc", "logica") task2 = Task("pinocchio_it_lingua_straniera", "acc", "lingua straniera") task3 = Task("pinocchio_it_matematica_e_scienze", "acc", "matematica e scienze") task4 = Task("pinocchio_it_diritto", "acc", "diritto") task5 = Task("pinocchio_it_cultura", "acc", "cultura") NUM_FEWSHOT = 0 # Change with your few shot # --------------------------------------------------- # Your leaderboard name TITLE = """

🇮🇹 Pinocchio ITA leaderboard from mii-llm🇮🇹

""" # What does your leaderboard evaluate? INTRODUCTION_TEXT = """ Pinocchio ITA leaderboard is an effort from mii-llm lab of creating specialized evaluations and models on Italian subjects. We also released the Pinocchio dataset a multimodal evaluation dataset for Italian tasks. If you want to reproduce the results we mantains a fork of lm-evaluation-harness, you can see an example in the About section. The open source models are evaluated on the following subjects on Pinocchio tasks: """ # Which evaluations are you running? how can people reproduce what you have? LLM_BENCHMARKS_TEXT = f""" ## How it works We released the Pinocchio dataset a multimodal evaluation dataset for Italian tasks based on original Italian text. If you want to reproduce the results we mantains a fork of lm-evaluation-harness for reproducing the dataset you can run the following command: ```bash lm_eval --model hf --model_args pretrained=anakin87/Phi-3.5-mini-ITA --tasks pinocchio_it_logica,pinocchio_it_generale,pinocchio_it_diritto,pinocchio_it_cultura,pinocchio_it_lingua_straniera,pinocchio_it_matematica_e_scienze --device cuda:0 --batch_size 1 ``` """ 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""" """