Spaces:
Running
Running
| from dataclasses import dataclass | |
| from enum import Enum | |
| import yaml | |
| import os | |
| class Task: | |
| benchmark: str | |
| metric: str | |
| col_name: str | |
| class Tasks(Enum): | |
| basic_understanding = Task("Basic Understanding", "acc", "Basic Understanding") | |
| contextual_analysis = Task("Contextual Analysis", "acc", "Contextual Analysis") | |
| deeper_implications = Task("Deeper Implications", "acc", "Deeper Implications") | |
| broader_implications = Task("Broader Implications", "acc", "Broader Implications") | |
| further_insights = Task("Further Insights", "acc", "Further Insights") | |
| NUM_FEWSHOT = 0 # Change with your few shot | |
| # --------------------------------------------------- | |
| # Your leaderboard name | |
| TITLE = """<body> | |
| <!-- Existing Header Content --> | |
| <h1 align="center" id="space-title">Multimodal LiveBench</h1> | |
| <h3 align="center">Zero-Contamination Evaluation for Multimodal Models on Lively Updated Internet Content</h3> | |
| </body>""" | |
| # What does your leaderboard evaluate? | |
| with open(os.path.join(os.path.dirname(__file__), "about.md"), "r") as f: | |
| INTRODUCTION_TEXT = f.read() | |
| def get_link(item): # name, icon, url): | |
| name = item["name"] | |
| icon = item.get("icon", None) | |
| url = item.get("url", "#") | |
| if icon.endswith(".svg"): | |
| icon_tag = f'<img src="{icon}" alt="{name}" style="height: 18px; width: 18px; display: inline;">' | |
| elif icon.startswith("fa-"): | |
| icon_tag = f'<i class="{icon}"></i>' | |
| elif not icon or icon == "": | |
| icon_tag = "" | |
| else: | |
| icon_tag = icon | |
| return f'{icon_tag} <a href="{url}" target="_blank">{name}</a>' | |
| with open(os.path.join(os.path.dirname(__file__), "links.yaml"), "r", encoding="utf-8") as f: | |
| links = yaml.safe_load(f) | |
| LINKS = "<center>" + " | ".join([get_link(item) for item in links]) + "</center>" | |
| # 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: | |
| """ | |
| 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{zhang2024lmmsevalrealitycheckevaluation, | |
| title={LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models}, | |
| author={Kaichen Zhang and Bo Li and Peiyuan Zhang and Fanyi Pu and Joshua Adrian Cahyono and Kairui Hu and Shuai Liu and Yuanhan Zhang and Jingkang Yang and Chunyuan Li and Ziwei Liu}, | |
| year={2024}, | |
| eprint={2407.12772}, | |
| archivePrefix={arXiv}, | |
| primaryClass={cs.CL}, | |
| url={https://arxiv.org/abs/2407.12772}, | |
| } | |
| """ | |