Spaces:
Sleeping
Sleeping
File size: 7,009 Bytes
df490c1 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 |
import abc
import gradio as gr
from gen_table import *
from meta_data import *
with gr.Blocks() as demo:
struct = load_results_local()
timestamp = struct['time']
EVAL_TIME = format_timestamp(timestamp)
results = struct['results']
N_MODEL = len(results)
N_DATA = len(results['Claude3-Sonnet']) - 1
DATASETS = list(results['Claude3-Sonnet'])
DATASETS.remove('META')
print(DATASETS)
gr.Markdown(LEADERBORAD_INTRODUCTION.format(N_MODEL, N_DATA, EVAL_TIME))
structs = [abc.abstractproperty() for _ in range(N_DATA)]
with gr.Tabs(elem_classes='tab-buttons') as tabs:
with gr.TabItem('🏅 Shopping MMLU Leaderboard', elem_id='main', id=0):
gr.Markdown(LEADERBOARD_MD['MAIN'])
_, check_box = BUILD_L1_DF(results, MAIN_FIELDS)
table = generate_table(results, DEFAULT_BENCH)
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',
interactive=True,
)
headers = ['Rank'] + check_box['essential'] + checkbox_group.value
with gr.Row():
model_size = gr.CheckboxGroup(
choices=MODEL_SIZE,
value=MODEL_SIZE,
label='Model Size',
interactive=True
)
model_type = gr.CheckboxGroup(
choices=MODEL_TYPE,
value=MODEL_TYPE,
label='Model Type',
interactive=True
)
print(headers)
print(check_box['essential'])
data_component = gr.components.DataFrame(
value=table[headers],
type='pandas',
datatype=[type_map[x] for x in headers],
interactive=False,
visible=True)
def filter_df(fields, model_size, model_type):
filter_list = ['Avg Score', 'Avg Rank', 'OpenSource', 'Verified']
headers = ['Rank'] + check_box['essential'] + fields
new_fields = [field for field in fields if field not in filter_list]
df = generate_table(results, new_fields)
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))
comp = gr.components.DataFrame(
value=df[headers],
type='pandas',
datatype=[type_map[x] for x in headers],
interactive=False,
visible=True)
return comp
for cbox in [checkbox_group, model_size, model_type]:
cbox.change(fn=filter_df, inputs=[checkbox_group, model_size, model_type], outputs=data_component)
with gr.TabItem('🔍 About', elem_id='about', id=1):
gr.Markdown(urlopen(SHOPPINGMMLU_README).read().decode())
for i, dataset in enumerate(DATASETS):
with gr.TabItem(f'📊 {dataset} Leaderboard', elem_id=dataset, id=i + 2):
if dataset in LEADERBOARD_MD:
gr.Markdown(LEADERBOARD_MD[dataset])
s = structs[i]
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',
interactive=True,
)
s.headers = ['Rank'] + s.check_box['essential'] + s.checkbox_group.value
print(s.check_box['essential'])
print(s.checkbox_group.value)
s.table['Rank'] = list(range(1, len(s.table) + 1))
print(s.headers)
with gr.Row():
s.model_size = gr.CheckboxGroup(
choices=MODEL_SIZE,
value=MODEL_SIZE,
label='Model Size',
interactive=True
)
s.model_type = gr.CheckboxGroup(
choices=MODEL_TYPE,
value=MODEL_TYPE,
label='Model Type',
interactive=True
)
s.data_component = gr.components.DataFrame(
value=s.table[s.headers],
type='pandas',
datatype=[s.type_map[x] for x in s.headers],
interactive=False,
visible=True)
s.dataset = gr.Textbox(value=dataset, label=dataset, visible=False)
def filter_df_l2(dataset_name, fields, model_size, model_type):
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))
comp = gr.components.DataFrame(
value=df[headers],
type='pandas',
datatype=[s.type_map[x] for x in headers],
interactive=False,
visible=True)
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_size, s.model_type],
outputs=s.data_component)
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')
|