Spaces:

allenai
/

ZebraLogic

Running

File size: 7,185 Bytes

from pathlib import Path
from collections import OrderedDict

DEFAULT_K = "∞"
# DEFAULT_K = "1500"

banner_url = "https://github.com/yuchenlin/ZeroEval/blob/main/docs/zebra/zebra_banner.png?raw=true" # the same repo here.
BANNER = f'<div style="display: flex; justify-content: flex-start;"><img src="{banner_url}" alt="Banner" style="width: 50vw; min-width: 300px; max-width: 800px;border: 3px solid gray; border-color: gray black;"> </div>'

TITLE = "<html> <head> <style> h1 {text-align: center;} </style> </head> <body> <h1> 🦁 AI2 WildBench Leaderboard </b> </body> </html>"
 
WINRATE_HEATMAP = "<div><img src='https://github.com/WildEval/WildBench-Leaderboard/blob/main/gradio/pairwise_win_fractions.png?raw=true' style='width:100%;'></div>"

CITATION_TEXT = """@article{lin2024wildbench,
    title={WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild},
    author={Bill Yuchen Lin and Yuntian Deng and Khyathi Chandu and Faeze Brahman and Abhilasha Ravichander and Valentina Pyatkin and Nouha Dziri and Ronan Le Bras and Yejin Choi},
    year={2024},
    eprint={2406.04770},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2406.04770}
}
"""

# make column_names as an ordered dict
 


column_names = OrderedDict({
    "Model": "Model",   
    "Mode": "Mode",
    "Puzzle Acc": "Puzzle Acc",
    "Cell Acc": "Cell Acc",
    "No answer": "No answer",
    "Easy Puzzle Acc": "Easy Puzzle Acc",
    "Hard Puzzle Acc": "Hard Puzzle Acc",
    # "Total Puzzles": "Total Puzzles",
    # "Reason Lens": "Reason Lens",
})



LEADERBOARD_REMARKS = """**WB Reward**: for each comparison (A vs B), a reward for A is **+/-1** if A is **much better/worse** than B, and **+/-0.5** if A is **slightly better/worse** than B; when there is a **Tie**, the reward is **0**.  
"""

# **WB Reward**: for each pairwise comparison, a reward for A is **+/-1** if A is **much better/worse** than B, and **+/-0.5** if A is **slightly better/worse** than B; 0 for a **Tie**.
# The baseline models are GPT4-Turbo, Haiku, and Llama2-70B, and Mix is the average of the three. 
# **WB Score** individually scores each model based on checklists.
# Evaluator is GPT-4-Turbo.
LEADERBOARD_REMARKS_MAIN = """ 
"""
  
RANKING_COLUMN = "Puzzle Acc"

ORDERED_COLUMN_NAMES = [
    "Model", 
    "Mode",
    "Puzzle Acc",
    "Easy Puzzle Acc",
    "Hard Puzzle Acc",
    "Cell Acc",
    "No answer", 
]

 
js_light = """
function refresh() {
    const url = new URL(window.location);

    if (url.searchParams.get('__theme') !== 'light') {
        url.searchParams.set('__theme', 'light');
        window.location.href = url.href;
    }

    // Find the fieldset with the given id
    const fieldset = document.getElementById("rank-column-radio");

    // Create a new span element with the text "Rank by:"
    const rankBySpan = document.createElement("span");
    rankBySpan.textContent = "Rank by: ";
    rankBySpan.style.fontWeight = "bold"; // Optional: make the text bold
     rankBySpan.style.fontSize = "19px"; // Larger font size
    rankBySpan.style.paddingRight = "18px"; // Add padding on the right

    // Wrap the span and the labels in a flex container
    const flexContainer = document.createElement("div");
    flexContainer.style.display = "flex";
    flexContainer.style.alignItems = "center";

    // Insert the rankBySpan at the beginning of the flex container
    flexContainer.appendChild(rankBySpan);

    // Move all existing labels into the flex container
    while (fieldset.firstChild) {
        flexContainer.appendChild(fieldset.firstChild);
    }

    // Append the flex container back to the fieldset
    fieldset.appendChild(flexContainer);
}
"""

js_code = """
function scroll_top() {
    console.log("Hello from Gradio!");  
    const bubbles = document.querySelectorAll('.bubble-wrap');
    bubbles.forEach((bubble, index) => {
        setTimeout(() => {
            bubble.scrollTop = 0;
        }, index * 100); // Delay of 100ms between each iteration
    });
    
} 
"""


TASK_TYPE_STR = "**Tasks**: Info seeking (**InfoSek**), Creative Writing (**CrtWrt**), Coding&Debugging (**Code**), Reasoning (**Reason**), Editing (**Edit**), **Math**, Planning (**Plan**), Brainstorming (**Brnstrm**), Role playing (**RolPly**), Advice seeking (**AdvSek**), Data Analysis (**DataAna**)"

css = """

 

code {
    font-size: large;
}
footer {visibility: hidden}
.top-left-LP{
    margin-top: 6px;
    margin-left: 5px;
}
.no_margin{
    margin-top: 0px;
    margin-left: 0px;
    margin-right: 0px;
    margin-bottom: 0px;
    padding-top: 0px;
    padding-left: 0px;
    padding-right: 0px;
    padding-bottom: 0px;
}
.markdown-text{font-size: 14pt}
.markdown-text-tiny{font-size: 10pt}
.markdown-text-small{font-size: 13pt}
.markdown-text-tiny{font-size: 12pt}
.markdown-text-tiny-red{
    font-size: 12pt;
    color: red;
    background-color: yellow;
    font-color: red;
    font-weight: bold;
}
th {
  text-align: center;
  font-size: 17px; /* Adjust the font size as needed */
}
td {
  font-size: 15px; /* Adjust the font size as needed */
  text-align: center;
}

.sample_button{
    border: 2px solid #000000;
    border-radius: 10px;
    padding: 10px;
    font-size: 17pt;
    font-weight: bold;
    margin: 5px;
    background-color: #D8BFD8;
}

.chat-common{
    height: auto;
    max-height: 400px;
    min-height: 100px; 
}
.chat-specific{
    height: auto;
    max-height: 600px;
    min-height: 200px; 
}
#od-benchmark-tab-table-button{
    font-size: 15pt;
    font-weight: bold;
} 

.btn_boderline{
    border: 1px solid #000000;
    border-radius: 5px;
    padding: 5px;
    margin: 5px;
    font-size: 15pt;
    font-weight: bold; 
}

.btn_boderline_next{
    border: 0.1px solid #000000;
    border-radius: 5px;
    padding: 5px;
    margin: 5px;
    font-size: 15pt;
    font-weight: bold; 
}

.btn_boderline_gray{
    border: 0.5px solid gray;
    border-radius: 5px;
    padding: 5px;
    margin: 5px;
    font-size: 15pt;
    font-weight: italic; 
}
.btn_boderline_selected{
    border: 2px solid purple;
    background-color: #f2f2f2;
    border-radius: 5px;
    padding: 5px;
    margin: 5px;
    font-size: 15pt;
    font-weight: bold;  
}
.accordion-label button span{
    font-size: 14pt;
    font-weight: bold;
} 

#show-task-categorized span{
    font-size: 13pt;
    font-weight: bold;
}

#show-open-source-models span{
    font-size: 13pt;
    font-weight: bold;
}

#select-models span{
    font-size: 10pt;
}

#select-tasks span{
    font-size: 10pt;
}


.markdown-text-details{
    margin: 10px;
    padding: 10px;
}


button.selected[role="tab"][aria-selected="true"] {
    font-size: 18px; /* or any other size you prefer */
    font-weight: bold;
}

#od-benchmark-tab-table-ablation-button {
    font-size: larger; /* Adjust the font size as needed */
}


.plotly-plot{
    height: auto;
    max-height: 600px;
    min-height: 600px; 
}

#length-margin-radio{
    font-size: 10pt;
    # padding: 0px;
    # margin: 1px;
}

#show-task-categorized{
    font-size: 12pt; 
    font-decoration: bold;
}

#show-open-source-models{
    font-size: 12pt; 
    font-decoration: bold;
}
"""