updated UI - Adithya S K
Browse files
app.py
CHANGED
@@ -61,67 +61,78 @@ def main():
|
|
61 |
with Leaderboard_tab:
|
62 |
data = get_data()
|
63 |
|
|
|
64 |
table_data = []
|
65 |
all_models = []
|
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 |
title = st.text_input('Model', placeholder=" 🔍 Search for your model (separate multiple queries with `;`) and press ENTER...")
|
117 |
|
118 |
on = st.checkbox('Sort by Language')
|
|
|
|
|
119 |
|
120 |
col1, col2 = st.columns(2)
|
121 |
with col1:
|
122 |
benchmark_options = st.multiselect(
|
123 |
'Pick Benchmark',
|
124 |
-
['ARC-Easy', 'ARC-Challenge', 'Hellaswag', 'Boolq','MMLU','Translation'],['ARC-Easy', 'ARC-Challenge', 'Hellaswag'
|
125 |
with col2:
|
126 |
language_options = st.multiselect(
|
127 |
'Pick Languages',
|
|
|
61 |
with Leaderboard_tab:
|
62 |
data = get_data()
|
63 |
|
64 |
+
|
65 |
table_data = []
|
66 |
all_models = []
|
67 |
+
try:
|
68 |
+
for item in data:
|
69 |
+
model_name = item.get("name")
|
70 |
+
language = item.get("language")
|
71 |
+
try:
|
72 |
+
ALL = item["result"]["all"]["acc_norm"]
|
73 |
+
except KeyError:
|
74 |
+
ALL = None
|
75 |
+
try:
|
76 |
+
ARC_Easy = item["result"]["ARC-Easy"]["acc_norm"]
|
77 |
+
except KeyError:
|
78 |
+
ARC_Easy = None
|
79 |
+
try:
|
80 |
+
ARC_Challenge = item["result"]["ARC-Challenge"]["acc_norm"]
|
81 |
+
except KeyError:
|
82 |
+
ARC_Challenge = None
|
83 |
+
try:
|
84 |
+
Hellaswag = item["result"]["Hellaswag"]["acc_norm"]
|
85 |
+
except KeyError:
|
86 |
+
Hellaswag = None
|
87 |
+
try:
|
88 |
+
Boolq = item["result"]["Boolq"]["acc_norm"]
|
89 |
+
except KeyError:
|
90 |
+
Boolq = None
|
91 |
+
try:
|
92 |
+
MMLU = item["result"]["MMLU"]["acc_norm"]
|
93 |
+
except KeyError:
|
94 |
+
MMLU = None
|
95 |
+
try:
|
96 |
+
Translation = item["result"]["Translation"]["acc_norm"]
|
97 |
+
except KeyError:
|
98 |
+
Translation = None
|
99 |
+
|
100 |
+
# If you are going through the code and wondering what is happening this code is a mess
|
101 |
|
102 |
+
all_models.append(model_name)
|
103 |
+
table_data.append({
|
104 |
+
"Model": model_name,
|
105 |
+
"Language": language,
|
106 |
+
"Avergae": ALL,
|
107 |
+
"ARC-Easy": ARC_Easy,
|
108 |
+
"ARC-Challenge": ARC_Challenge,
|
109 |
+
"Hellaswag": Hellaswag,
|
110 |
+
"Boolq": Boolq,
|
111 |
+
"MMLU": MMLU,
|
112 |
+
"Translation": Translation,
|
113 |
+
})
|
114 |
+
|
115 |
+
df = pd.DataFrame(table_data)
|
116 |
+
except:
|
117 |
+
columns = ["Model", "Language", "Avergae", "ARC-Easy", "ARC-Challenge", "Hellaswag", "Boolq", "MMLU", "Translation"]
|
118 |
+
# Create an empty list to hold the data
|
119 |
+
table_data = []
|
120 |
+
# Append an empty dictionary with column names as keys to the table_data list
|
121 |
+
table_data.append({col: None for col in columns})
|
122 |
+
# Create a DataFrame from the table_data list
|
123 |
+
df = pd.DataFrame(table_data)
|
124 |
|
125 |
title = st.text_input('Model', placeholder=" 🔍 Search for your model (separate multiple queries with `;`) and press ENTER...")
|
126 |
|
127 |
on = st.checkbox('Sort by Language')
|
128 |
+
|
129 |
+
st.text("Boolq , MMLU , Translation is still being tested")
|
130 |
|
131 |
col1, col2 = st.columns(2)
|
132 |
with col1:
|
133 |
benchmark_options = st.multiselect(
|
134 |
'Pick Benchmark',
|
135 |
+
['ARC-Easy', 'ARC-Challenge', 'Hellaswag', 'Boolq','MMLU','Translation'],['ARC-Easy', 'ARC-Challenge', 'Hellaswag'])
|
136 |
with col2:
|
137 |
language_options = st.multiselect(
|
138 |
'Pick Languages',
|