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("tmlu", "acc,none", "TMLU") task1 = Task("twllm_eval", "acc,none", "TW Truthful QA") task2 = Task("tw_legal", "acc,none", "TW Legal Eval") task3 = Task("mmlu", "acc,none", "MMLU") NUM_FEWSHOT = 0 # Change with your few shot # --------------------------------------------------- # Your leaderboard name TITLE = """

Demo leaderboard

""" # What does your leaderboard evaluate? INTRODUCTION_TEXT = """ Intro text """ # 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: please checkout this command https://github.com/adamlin120/lm-evaluation-harness/blob/main/run_all.sh """ 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""" @misc{open-tw-llm-leaderboard, author = {Yen{-}Ting Lin, Yun{-}Nung Chen}, title = {Open TW-LLM Leaderboard}, year = {2024}, publisher = {National Taiwan University}, howpublished = "\url{https://huggingface.co/spaces/yentinglin/open-tw-llm-leaderboard}" } @article{DBLP:journals/corr/abs-2403-20180, author = {Po{-}Heng Chen and Sijia Cheng and Wei{-}Lin Chen and Yen{-}Ting Lin and Yun{-}Nung Chen}, title = {Measuring Taiwanese Mandarin Language Understanding}, journal = {CoRR}, volume = {abs/2403.20180}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2403.20180}, doi = {10.48550/ARXIV.2403.20180}, eprinttype = {arXiv}, eprint = {2403.20180}, timestamp = {Wed, 10 Apr 2024 17:37:45 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2403-20180.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } @misc{hendrycks2021measuring, title={Measuring Massive Multitask Language Understanding}, author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt}, year={2021}, eprint={2009.03300}, archivePrefix={arXiv}, primaryClass={cs.CY} } @software{eval-harness, author = {Gao, Leo and Tow, Jonathan and Biderman, Stella and Black, Sid and DiPofi, Anthony and Foster, Charles and Golding, Laurence and Hsu, Jeffrey and McDonell, Kyle and Muennighoff, Niklas and Phang, Jason and Reynolds, Laria and Tang, Eric and Thite, Anish and Wang, Ben and Wang, Kevin and Zou, Andy}, title = {A framework for few-shot language model evaluation}, month = sep, year = 2021, publisher = {Zenodo}, version = {v0.0.1}, doi = {10.5281/zenodo.5371628}, url = {https://doi.org/10.5281/zenodo.5371628} } """