File size: 6,180 Bytes
ad8152e 033a696 ad8152e 1b0ca05 ad8152e 1b0ca05 ad8152e 1b0ca05 033a696 ad8152e 033a696 ad8152e 033a696 ad8152e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 |
import abc
import gradio as gr
from gen_table import *
from meta_data import *
head_style = """
<style>
@media (min-width: 1536px)
{
.gradio-container {
min-width: var(--size-full) !important;
}
}
</style>
"""
def math_main_tab(results):
_, check_box = BUILD_L1_DF(results)
table = generate_table(results)
table['Rank'] = list(range(1, len(table) + 1))
type_map = check_box['type_map']
type_map['Rank'] = 'number'
checkbox_group = gr.CheckboxGroup(choices=check_box['all'], value=check_box['required'], label='Evaluation Dimension')
headers = ['Rank'] + check_box['essential'] + checkbox_group.value
with gr.Row():
model_name = gr.Textbox(value='Input the Model Name (fuzzy)', label='Model Name')
model_size = gr.CheckboxGroup(choices=MODEL_SIZE, value=MODEL_SIZE, label='Model Size')
model_type = gr.CheckboxGroup(choices=MODEL_TYPE, value=MODEL_TYPE, label='Model Type')
data_component = gr.components.DataFrame(value=table[headers], datatype=[type_map[x] for x in headers])
def filter_df(fields, model_name, model_size, model_type):
results = load_results()['results']
headers = ['Rank'] + check_box['essential'] + fields
df = generate_table(results)
df['flag'] = [model_size_flag(x, model_size) for x in df['Param (B)']]
df = df[df['flag']]
df.pop('flag')
if len(df):
df['flag'] = [model_type_flag(df.iloc[i], model_type) for i in range(len(df))]
df = df[df['flag']]
df.pop('flag')
df['Rank'] = list(range(1, len(df) + 1))
default_val = 'Input the Model Name (fuzzy)'
if model_name != default_val:
method_names = [x.split('</a>')[0].split('>')[-1].lower() for x in df['Method']]
flag = [model_name.lower() in name for name in method_names]
df['TEMP'] = flag
df = df[df['TEMP'] == True]
df.pop('TEMP')
comp = gr.components.DataFrame(value=df[headers], datatype=[type_map[x] for x in headers])
return comp
for cbox in [checkbox_group, model_size, model_type]:
cbox.change(fn=filter_df, inputs=[checkbox_group, model_name, model_size, model_type], outputs=data_component)
model_name.submit(fn=filter_df, inputs=[checkbox_group, model_name, model_size, model_type], outputs=data_component)
def dataset_tab(results, struct, dataset):
s = struct
s.table, s.check_box = BUILD_L2_DF(results, dataset)
s.type_map = s.check_box['type_map']
s.type_map['Rank'] = 'number'
s.checkbox_group = gr.CheckboxGroup(choices=s.check_box['all'], value=s.check_box['required'], label=f'{dataset} CheckBoxes')
s.headers = ['Rank'] + s.check_box['essential'] + s.checkbox_group.value
s.table['Rank'] = list(range(1, len(s.table) + 1))
with gr.Row():
s.model_name = gr.Textbox(value='Input the Model Name (fuzzy)', label='Model Name')
s.model_size = gr.CheckboxGroup(choices=MODEL_SIZE, value=MODEL_SIZE, label='Model Size')
s.model_type = gr.CheckboxGroup(choices=MODEL_TYPE, value=MODEL_TYPE, label='Model Type')
s.data_component = gr.components.DataFrame(value=s.table[s.headers], datatype=[s.type_map[x] for x in s.headers])
s.dataset = gr.Textbox(value=dataset, label=dataset, visible=False)
def filter_df_l2(dataset_name, fields, model_name, model_size, model_type):
results = load_results()['results']
s = structs[DATASETS.index(dataset_name)]
headers = ['Rank'] + s.check_box['essential'] + fields
df = cp.deepcopy(s.table)
df['flag'] = [model_size_flag(x, model_size) for x in df['Param (B)']]
df = df[df['flag']]
df.pop('flag')
if len(df):
df['flag'] = [model_type_flag(df.iloc[i], model_type) for i in range(len(df))]
df = df[df['flag']]
df.pop('flag')
df['Rank'] = list(range(1, len(df) + 1))
default_val = 'Input the Model Name (fuzzy)'
if model_name != default_val:
method_names = [x.split('</a>')[0].split('>')[-1].lower() for x in df['Method']]
flag = [model_name.lower() in name for name in method_names]
df['TEMP'] = flag
df = df[df['TEMP'] == True]
df.pop('TEMP')
comp = gr.components.DataFrame(value=df[headers], datatype=[s.type_map[x] for x in headers])
return comp
for cbox in [s.checkbox_group, s.model_size, s.model_type]:
cbox.change(
fn=filter_df_l2,
inputs=[s.dataset, s.checkbox_group, s.model_name, s.model_size, s.model_type],
outputs=s.data_component)
s.model_name.submit(
fn=filter_df_l2,
inputs=[s.dataset, s.checkbox_group, s.model_name, s.model_size, s.model_type],
outputs=s.data_component)
with gr.Blocks(title="Math Leaderboard", head=head_style) as demo:
results = load_results()['results']
N_MODEL = len(results)
DATASETS = []
for m in results:
DATASETS.extend(results[m].keys())
DATASETS = [d for d in set(DATASETS) if d != 'META']
N_DATA = len(DATASETS)
structs = [abc.abstractproperty() for _ in range(N_DATA)]
gr.Markdown(LEADERBORAD_INTRODUCTION)
with gr.Tabs(elem_classes='tab-buttons') as tabs:
with gr.TabItem('🏅 LMM Math Leaderboard', elem_id='main', id=0):
math_main_tab(results)
for i, dataset in enumerate(DATASETS):
tab_name_map = {
'MathVista': 'MathVista (Test Mini)',
'MathVerse': 'MathVerse (Vision Only)',
}
with gr.TabItem(
f'📊 {dataset if dataset not in tab_name_map else tab_name_map[dataset]}', elem_id=dataset, id=i + 2):
dataset_tab(results, structs[i], dataset)
with gr.Row():
with gr.Accordion('Citation', open=False):
citation_button = gr.Textbox(
value=CITATION_BUTTON_TEXT,
label=CITATION_BUTTON_LABEL,
elem_id='citation-button')
if __name__ == '__main__':
demo.launch(server_name='0.0.0.0')
|