File size: 7,586 Bytes
219b840 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 |
import gradio as gr
import pandas as pd
from pathlib import Path
abs_path = Path(__file__).parent.absolute()
df = pd.read_json(str(abs_path / "assets/leaderboard_data.json"))
invisible_df = df.copy()
COLS = [
"T",
"Model",
"Average ⬆️",
"ARC",
"HellaSwag",
"MMLU",
"TruthfulQA",
"Winogrande",
"GSM8K",
"Type",
"Architecture",
"Precision",
"Merged",
"Hub License",
"#Params (B)",
"Hub ❤️",
"Model sha",
"model_name_for_query",
]
ON_LOAD_COLS = [
"T",
"Model",
"Average ⬆️",
"ARC",
"HellaSwag",
"MMLU",
"TruthfulQA",
"Winogrande",
"GSM8K",
"model_name_for_query",
]
TYPES = [
"str",
"markdown",
"number",
"number",
"number",
"number",
"number",
"number",
"number",
"str",
"str",
"str",
"str",
"bool",
"str",
"number",
"number",
"bool",
"str",
"bool",
"bool",
"str",
]
NUMERIC_INTERVALS = {
"?": pd.Interval(-1, 0, closed="right"),
"~1.5": pd.Interval(0, 2, closed="right"),
"~3": pd.Interval(2, 4, closed="right"),
"~7": pd.Interval(4, 9, closed="right"),
"~13": pd.Interval(9, 20, closed="right"),
"~35": pd.Interval(20, 45, closed="right"),
"~60": pd.Interval(45, 70, closed="right"),
"70+": pd.Interval(70, 10000, closed="right"),
}
MODEL_TYPE = [str(s) for s in df["T"].unique()]
Precision = [str(s) for s in df["Precision"].unique()]
# Searching and filtering
def update_table(
hidden_df: pd.DataFrame,
columns: list,
type_query: list,
precision_query: str,
size_query: list,
query: str,
):
filtered_df = filter_models(hidden_df, type_query, size_query, precision_query) # type: ignore
filtered_df = filter_queries(query, filtered_df)
df = select_columns(filtered_df, columns)
return df
def search_table(df: pd.DataFrame, query: str) -> pd.DataFrame:
return df[(df["model_name_for_query"].str.contains(query, case=False))] # type: ignore
def select_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
# We use COLS to maintain sorting
filtered_df = df[[c for c in COLS if c in df.columns and c in columns]]
return filtered_df # type: ignore
def filter_queries(query: str, filtered_df: pd.DataFrame) -> pd.DataFrame:
final_df = []
if query != "":
queries = [q.strip() for q in query.split(";")]
for _q in queries:
_q = _q.strip()
if _q != "":
temp_filtered_df = search_table(filtered_df, _q)
if len(temp_filtered_df) > 0:
final_df.append(temp_filtered_df)
if len(final_df) > 0:
filtered_df = pd.concat(final_df)
filtered_df = filtered_df.drop_duplicates( # type: ignore
subset=["Model", "Precision", "Model sha"]
)
return filtered_df
def filter_models(
df: pd.DataFrame,
type_query: list,
size_query: list,
precision_query: list,
) -> pd.DataFrame:
# Show all models
filtered_df = df
type_emoji = [t[0] for t in type_query]
filtered_df = filtered_df.loc[df["T"].isin(type_emoji)]
filtered_df = filtered_df.loc[df["Precision"].isin(precision_query + ["None"])]
numeric_interval = pd.IntervalIndex(
sorted([NUMERIC_INTERVALS[s] for s in size_query]) # type: ignore
)
params_column = pd.to_numeric(df["#Params (B)"], errors="coerce")
mask = params_column.apply(lambda x: any(numeric_interval.contains(x))) # type: ignore
filtered_df = filtered_df.loc[mask]
return filtered_df
demo = gr.Blocks(css=str(abs_path / "assets/leaderboard_data.json"))
with demo:
gr.Markdown("""Test Space of the LLM Leaderboard""", elem_classes="markdown-text")
with gr.Tabs(elem_classes="tab-buttons") as tabs:
with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
with gr.Row():
with gr.Column():
with gr.Row():
search_bar = gr.Textbox(
placeholder=" 🔍 Search for your model (separate multiple queries with `;`) and press ENTER...",
show_label=False,
elem_id="search-bar",
)
with gr.Row():
shown_columns = gr.CheckboxGroup(
choices=COLS,
value=ON_LOAD_COLS,
label="Select columns to show",
elem_id="column-select",
interactive=True,
)
with gr.Column(min_width=320):
filter_columns_type = gr.CheckboxGroup(
label="Model types",
choices=MODEL_TYPE,
value=MODEL_TYPE,
interactive=True,
elem_id="filter-columns-type",
)
filter_columns_precision = gr.CheckboxGroup(
label="Precision",
choices=Precision,
value=Precision,
interactive=True,
elem_id="filter-columns-precision",
)
filter_columns_size = gr.CheckboxGroup(
label="Model sizes (in billions of parameters)",
choices=list(NUMERIC_INTERVALS.keys()),
value=list(NUMERIC_INTERVALS.keys()),
interactive=True,
elem_id="filter-columns-size",
)
leaderboard_table = gr.components.Dataframe(
value=df[ON_LOAD_COLS], # type: ignore
headers=ON_LOAD_COLS,
datatype=TYPES,
elem_id="leaderboard-table",
interactive=False,
visible=True,
column_widths=["2%", "33%"],
)
# Dummy leaderboard for handling the case when the user uses backspace key
hidden_leaderboard_table_for_search = gr.components.Dataframe(
value=invisible_df[COLS], # type: ignore
headers=COLS,
datatype=TYPES,
visible=False,
)
search_bar.submit(
update_table,
[
hidden_leaderboard_table_for_search,
shown_columns,
filter_columns_type,
filter_columns_precision,
filter_columns_size,
search_bar,
],
leaderboard_table,
)
for selector in [
shown_columns,
filter_columns_type,
filter_columns_precision,
filter_columns_size,
]:
selector.change(
update_table,
[
hidden_leaderboard_table_for_search,
shown_columns,
filter_columns_type,
filter_columns_precision,
filter_columns_size,
search_bar,
],
leaderboard_table,
queue=True,
)
if __name__ == "__main__":
demo.queue(default_concurrency_limit=40).launch()
|