ycy commited on
Commit
cce655b
Β·
1 Parent(s): 5bd8771
Files changed (2) hide show
  1. app.py +55 -55
  2. src/about.py +8 -7
app.py CHANGED
@@ -102,61 +102,61 @@ with demo:
102
  with gr.TabItem("πŸ“ About", elem_id="llm-benchmark-tab-table", id=2):
103
  gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
104
 
105
- with gr.TabItem("πŸš€ Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
106
- with gr.Column():
107
- with gr.Row():
108
- gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
109
-
110
- # with gr.Column():
111
- # with gr.Accordion(
112
- # f"βœ… Finished Evaluations ({len(finished_eval_queue_df)})",
113
- # open=False,
114
- # ):
115
- # with gr.Row():
116
- # finished_eval_table = gr.components.Dataframe(
117
- # value=finished_eval_queue_df,
118
- # headers=EVAL_COLS,
119
- # datatype=EVAL_TYPES,
120
- # row_count=5,
121
- # )
122
- # with gr.Accordion(
123
- # f"πŸ”„ Running Evaluation Queue ({len(running_eval_queue_df)})",
124
- # open=False,
125
- # ):
126
- # with gr.Row():
127
- # running_eval_table = gr.components.Dataframe(
128
- # value=running_eval_queue_df,
129
- # headers=EVAL_COLS,
130
- # datatype=EVAL_TYPES,
131
- # row_count=5,
132
- # )
133
-
134
- # with gr.Accordion(
135
- # f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
136
- # open=False,
137
- # ):
138
- # with gr.Row():
139
- # pending_eval_table = gr.components.Dataframe(
140
- # value=pending_eval_queue_df,
141
- # headers=EVAL_COLS,
142
- # datatype=EVAL_TYPES,
143
- # row_count=5,
144
- # )
145
- with gr.Row():
146
- gr.Markdown("# βœ‰οΈβœ¨ Submit Open model here!", elem_classes="markdown-text")
147
-
148
- with gr.Row():
149
- with gr.Column():
150
- model_name = gr.Textbox(label="Model name")
151
- submit_button = gr.Button("Submit Eval")
152
- submission_result = gr.Markdown()
153
- submit_button.click(
154
- add_new_open_model_eval,
155
- [
156
- model_name
157
- ],
158
- submission_result,
159
- )
160
 
161
  with gr.Row():
162
  with gr.Accordion("πŸ“™ Citation", open=False):
 
102
  with gr.TabItem("πŸ“ About", elem_id="llm-benchmark-tab-table", id=2):
103
  gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
104
 
105
+ # with gr.TabItem("πŸš€ Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
106
+ # with gr.Column():
107
+ # with gr.Row():
108
+ # gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
109
+
110
+ # # with gr.Column():
111
+ # # with gr.Accordion(
112
+ # # f"βœ… Finished Evaluations ({len(finished_eval_queue_df)})",
113
+ # # open=False,
114
+ # # ):
115
+ # # with gr.Row():
116
+ # # finished_eval_table = gr.components.Dataframe(
117
+ # # value=finished_eval_queue_df,
118
+ # # headers=EVAL_COLS,
119
+ # # datatype=EVAL_TYPES,
120
+ # # row_count=5,
121
+ # # )
122
+ # # with gr.Accordion(
123
+ # # f"πŸ”„ Running Evaluation Queue ({len(running_eval_queue_df)})",
124
+ # # open=False,
125
+ # # ):
126
+ # # with gr.Row():
127
+ # # running_eval_table = gr.components.Dataframe(
128
+ # # value=running_eval_queue_df,
129
+ # # headers=EVAL_COLS,
130
+ # # datatype=EVAL_TYPES,
131
+ # # row_count=5,
132
+ # # )
133
+
134
+ # # with gr.Accordion(
135
+ # # f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
136
+ # # open=False,
137
+ # # ):
138
+ # # with gr.Row():
139
+ # # pending_eval_table = gr.components.Dataframe(
140
+ # # value=pending_eval_queue_df,
141
+ # # headers=EVAL_COLS,
142
+ # # datatype=EVAL_TYPES,
143
+ # # row_count=5,
144
+ # # )
145
+ # with gr.Row():
146
+ # gr.Markdown("# βœ‰οΈβœ¨ Submit Open model here!", elem_classes="markdown-text")
147
+
148
+ # with gr.Row():
149
+ # with gr.Column():
150
+ # model_name = gr.Textbox(label="Model name")
151
+ # submit_button = gr.Button("Submit Eval")
152
+ # submission_result = gr.Markdown()
153
+ # submit_button.click(
154
+ # add_new_open_model_eval,
155
+ # [
156
+ # model_name
157
+ # ],
158
+ # submission_result,
159
+ # )
160
 
161
  with gr.Row():
162
  with gr.Accordion("πŸ“™ Citation", open=False):
src/about.py CHANGED
@@ -71,13 +71,14 @@ INTRODUCE_BENCHMARK = f"""
71
 
72
  #TODO About
73
  LLM_BENCHMARKS_TEXT = f"""
74
- <h2 style="color: #2c3e50;"> Why Leaderboard? </h2>
75
- <h2 style="color: #2c3e50;">How it works</h2>
76
-
77
- <h2 style="color: #2c3e50;">Datasets</h2>
78
- <h2 style="color: #2c3e50;">Metrics</h2>
79
- To reproduce our results, here is the commands you can run:
80
-
 
81
  """
82
 
83
  EVALUATION_QUEUE_TEXT = """
 
71
 
72
  #TODO About
73
  LLM_BENCHMARKS_TEXT = f"""
74
+ <div style="text-align: center; margin: 20px;">
75
+ <h2 style="color: #2c3e50; font-family: Arial, sans-serif;"> See details in
76
+ <a href="https://github.com/njucckevin/CapArena" target="_blank"
77
+ style="color: #2980b9; text-decoration: none; font-weight: bold;">
78
+ CapArena
79
+ </a>
80
+ </h2>
81
+ </div>
82
  """
83
 
84
  EVALUATION_QUEUE_TEXT = """