zhuohan-7 commited on
Commit
a40ee94
·
verified ·
1 Parent(s): 4c054d2

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. app/draw_diagram.py +1 -0
  2. app/pages.py +27 -9
app/draw_diagram.py CHANGED
@@ -341,6 +341,7 @@ def draw_only_acc(folder_name, category_one, category_two, sorted):
341
  .stMultiSelect [data-baseweb=select] span{
342
  max-width: 800px;
343
  font-size: 0.9rem;
 
344
  }
345
  </style>
346
  """, unsafe_allow_html=True)
 
341
  .stMultiSelect [data-baseweb=select] span{
342
  max-width: 800px;
343
  font-size: 0.9rem;
344
+ color: blue; /* Change text color of selected options */
345
  }
346
  </style>
347
  """, unsafe_allow_html=True)
app/pages.py CHANGED
@@ -15,7 +15,7 @@ def dashboard():
15
  seaeval_url = "https://seaeval.github.io/"
16
 
17
  st.divider()
18
- st.markdown("#### What is [SeaEval](%s)" % seaeval_url)
19
 
20
  with st.container():
21
  left_co, cent_co,last_co = st.columns(3)
@@ -26,7 +26,7 @@ def dashboard():
26
  st.markdown('''
27
 
28
  ''')
29
- st.markdown("##### A new benchmark for multilingual foundation models consisting of 28 dataset.")
30
  st.markdown(''':star: How models understand and reason with natural language?
31
  :balloon: Languages: English, Chinese, Malay, Spainish, Indonedian, Vietnamese, Filipino.
32
  ''')
@@ -104,11 +104,15 @@ def cultural_reasoning():
104
  st.title("Cultural Reasoning")
105
 
106
  filters_levelone = ['Zero Shot', 'Few Shot']
107
- filters_leveltwo = ['SG EVAL',
108
- 'SG EVAL V1 Cleaned',
109
  'SG EVAL V2 MCQ',
110
  'SG EVAL V2 Open Ended',
111
- 'CN EVAL', 'PH EVAL', 'US EVAL']
 
 
 
 
 
112
 
113
  category_one_dict = {'Zero Shot': 'zero_shot',
114
  'Few Shot': 'few_shot'}
@@ -132,7 +136,13 @@ def general_reasoning():
132
  st.title("General Reasoning")
133
 
134
  filters_levelone = ['Zero Shot', 'Few Shot']
135
- filters_leveltwo = ['MMLU', 'C Eval', 'CMMLU', 'ZBench', 'IndoMMLU']
 
 
 
 
 
 
136
 
137
  category_one_dict = {'Zero Shot': 'zero_shot',
138
  'Few Shot': 'few_shot'}
@@ -158,7 +168,8 @@ def flores():
158
  filters_leveltwo = ['Indonesian to English',
159
  'Vitenamese to English',
160
  'Chinese to English',
161
- 'Malay to English']
 
162
 
163
  category_one_dict = {'Zero Shot': 'zero_shot',
164
  'Few Shot': 'few_shot'}
@@ -182,7 +193,10 @@ def emotion():
182
  st.title("Emotion")
183
 
184
  filters_levelone = ['Zero Shot', 'Few Shot']
185
- filters_leveltwo = ['Indonesian Emotion Classification', 'SST2']
 
 
 
186
 
187
  category_one_dict = {'Zero Shot': 'zero_shot',
188
  'Few Shot': 'few_shot'}
@@ -205,7 +219,11 @@ def dialogue():
205
  st.title("Dialogue")
206
 
207
  filters_levelone = ['Zero Shot', 'Few Shot']
208
- filters_leveltwo = ['DREAM', 'SAMSum', 'DialogSum']
 
 
 
 
209
 
210
  category_one_dict = {'Zero Shot': 'zero_shot',
211
  'Few Shot': 'few_shot'}
 
15
  seaeval_url = "https://seaeval.github.io/"
16
 
17
  st.divider()
18
+ st.markdown("#### What is [SeaEval](%s)?" % seaeval_url)
19
 
20
  with st.container():
21
  left_co, cent_co,last_co = st.columns(3)
 
26
  st.markdown('''
27
 
28
  ''')
29
+ st.markdown("##### A new benchmark for multilingual, multicultral foundation model evaluation consisting of 28 dataset as the core and keep expanding over time.")
30
  st.markdown(''':star: How models understand and reason with natural language?
31
  :balloon: Languages: English, Chinese, Malay, Spainish, Indonedian, Vietnamese, Filipino.
32
  ''')
 
104
  st.title("Cultural Reasoning")
105
 
106
  filters_levelone = ['Zero Shot', 'Few Shot']
107
+ filters_leveltwo = [
 
108
  'SG EVAL V2 MCQ',
109
  'SG EVAL V2 Open Ended',
110
+ 'SG EVAL',
111
+ 'SG EVAL V1 Cleaned',
112
+ 'CN EVAL',
113
+ 'PH EVAL',
114
+ 'US EVAL'
115
+ ]
116
 
117
  category_one_dict = {'Zero Shot': 'zero_shot',
118
  'Few Shot': 'few_shot'}
 
136
  st.title("General Reasoning")
137
 
138
  filters_levelone = ['Zero Shot', 'Few Shot']
139
+ filters_leveltwo = [
140
+ 'MMLU',
141
+ 'CMMLU',
142
+ 'IndoMMLU',
143
+ 'C Eval',
144
+ 'ZBench',
145
+ ]
146
 
147
  category_one_dict = {'Zero Shot': 'zero_shot',
148
  'Few Shot': 'few_shot'}
 
168
  filters_leveltwo = ['Indonesian to English',
169
  'Vitenamese to English',
170
  'Chinese to English',
171
+ 'Malay to English'
172
+ ]
173
 
174
  category_one_dict = {'Zero Shot': 'zero_shot',
175
  'Few Shot': 'few_shot'}
 
193
  st.title("Emotion")
194
 
195
  filters_levelone = ['Zero Shot', 'Few Shot']
196
+ filters_leveltwo = [
197
+ 'Indonesian Emotion Classification',
198
+ 'SST2',
199
+ ]
200
 
201
  category_one_dict = {'Zero Shot': 'zero_shot',
202
  'Few Shot': 'few_shot'}
 
219
  st.title("Dialogue")
220
 
221
  filters_levelone = ['Zero Shot', 'Few Shot']
222
+ filters_leveltwo = [
223
+ 'DREAM',
224
+ 'SAMSum',
225
+ 'DialogSum',
226
+ ]
227
 
228
  category_one_dict = {'Zero Shot': 'zero_shot',
229
  'Few Shot': 'few_shot'}