Spaces:
Runtime error
Runtime error
unknown
commited on
Commit
β’
9486003
1
Parent(s):
6e1b242
update app.py and about.py test
Browse files- app.py +88 -88
- src/about.py +3 -3
app.py
CHANGED
@@ -138,7 +138,7 @@ with demo:
|
|
138 |
gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
|
139 |
|
140 |
with gr.Tabs(elem_classes="tab-buttons") as tabs:
|
141 |
-
with gr.TabItem("
|
142 |
with gr.Row():
|
143 |
with gr.Column():
|
144 |
with gr.Row():
|
@@ -239,95 +239,95 @@ with demo:
|
|
239 |
queue=True,
|
240 |
)
|
241 |
|
242 |
-
with gr.TabItem("π
|
243 |
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
244 |
|
245 |
-
with gr.TabItem("π Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
|
253 |
-
|
254 |
-
|
255 |
-
|
256 |
-
|
257 |
-
|
258 |
-
|
259 |
-
|
260 |
-
|
261 |
-
|
262 |
-
|
263 |
-
|
264 |
-
|
265 |
-
|
266 |
-
|
267 |
-
|
268 |
-
|
269 |
-
|
270 |
-
|
271 |
-
|
272 |
-
|
273 |
-
|
274 |
-
|
275 |
-
|
276 |
-
|
277 |
-
|
278 |
-
|
279 |
-
|
280 |
-
|
281 |
-
|
282 |
-
|
283 |
-
|
284 |
-
|
285 |
-
|
286 |
-
|
287 |
-
|
288 |
-
|
289 |
-
|
290 |
-
|
291 |
-
|
292 |
-
|
293 |
-
|
294 |
-
|
295 |
-
|
296 |
-
|
297 |
-
|
298 |
-
|
299 |
-
|
300 |
-
|
301 |
-
|
302 |
-
|
303 |
-
|
304 |
-
|
305 |
-
|
306 |
-
|
307 |
-
|
308 |
-
|
309 |
-
|
310 |
-
|
311 |
-
|
312 |
-
|
313 |
-
|
314 |
-
|
315 |
-
|
316 |
-
|
317 |
-
|
318 |
-
|
319 |
-
|
320 |
-
|
321 |
-
|
322 |
-
|
323 |
-
|
324 |
-
|
325 |
-
|
326 |
-
|
327 |
-
|
328 |
-
|
329 |
-
|
330 |
-
|
331 |
|
332 |
with gr.Row():
|
333 |
with gr.Accordion("π Citation", open=False):
|
|
|
138 |
gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
|
139 |
|
140 |
with gr.Tabs(elem_classes="tab-buttons") as tabs:
|
141 |
+
with gr.TabItem("π μ§ν μ€ κ³Όμ ", elem_id="llm-benchmark-tab-table", id=0):
|
142 |
with gr.Row():
|
143 |
with gr.Column():
|
144 |
with gr.Row():
|
|
|
239 |
queue=True,
|
240 |
)
|
241 |
|
242 |
+
with gr.TabItem("π μ§λ κ³Όμ ", elem_id="llm-benchmark-tab-table", id=2):
|
243 |
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
244 |
|
245 |
+
# with gr.TabItem("π Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
|
246 |
+
# with gr.Column():
|
247 |
+
# with gr.Row():
|
248 |
+
# gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
|
249 |
+
|
250 |
+
# with gr.Column():
|
251 |
+
# with gr.Accordion(
|
252 |
+
# f"β
Finished Evaluations ({len(finished_eval_queue_df)})",
|
253 |
+
# open=False,
|
254 |
+
# ):
|
255 |
+
# with gr.Row():
|
256 |
+
# finished_eval_table = gr.components.Dataframe(
|
257 |
+
# value=finished_eval_queue_df,
|
258 |
+
# headers=EVAL_COLS,
|
259 |
+
# datatype=EVAL_TYPES,
|
260 |
+
# row_count=5,
|
261 |
+
# )
|
262 |
+
# with gr.Accordion(
|
263 |
+
# f"π Running Evaluation Queue ({len(running_eval_queue_df)})",
|
264 |
+
# open=False,
|
265 |
+
# ):
|
266 |
+
# with gr.Row():
|
267 |
+
# running_eval_table = gr.components.Dataframe(
|
268 |
+
# value=running_eval_queue_df,
|
269 |
+
# headers=EVAL_COLS,
|
270 |
+
# datatype=EVAL_TYPES,
|
271 |
+
# row_count=5,
|
272 |
+
# )
|
273 |
+
|
274 |
+
# with gr.Accordion(
|
275 |
+
# f"β³ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
|
276 |
+
# open=False,
|
277 |
+
# ):
|
278 |
+
# with gr.Row():
|
279 |
+
# pending_eval_table = gr.components.Dataframe(
|
280 |
+
# value=pending_eval_queue_df,
|
281 |
+
# headers=EVAL_COLS,
|
282 |
+
# datatype=EVAL_TYPES,
|
283 |
+
# row_count=5,
|
284 |
+
# )
|
285 |
+
# with gr.Row():
|
286 |
+
# gr.Markdown("# βοΈβ¨ Submit your model here!", elem_classes="markdown-text")
|
287 |
+
|
288 |
+
# with gr.Row():
|
289 |
+
# with gr.Column():
|
290 |
+
# model_name_textbox = gr.Textbox(label="Model name")
|
291 |
+
# revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
|
292 |
+
# model_type = gr.Dropdown(
|
293 |
+
# choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
|
294 |
+
# label="Model type",
|
295 |
+
# multiselect=False,
|
296 |
+
# value=None,
|
297 |
+
# interactive=True,
|
298 |
+
# )
|
299 |
+
|
300 |
+
# with gr.Column():
|
301 |
+
# precision = gr.Dropdown(
|
302 |
+
# choices=[i.value.name for i in Precision if i != Precision.Unknown],
|
303 |
+
# label="Precision",
|
304 |
+
# multiselect=False,
|
305 |
+
# value="float16",
|
306 |
+
# interactive=True,
|
307 |
+
# )
|
308 |
+
# weight_type = gr.Dropdown(
|
309 |
+
# choices=[i.value.name for i in WeightType],
|
310 |
+
# label="Weights type",
|
311 |
+
# multiselect=False,
|
312 |
+
# value="Original",
|
313 |
+
# interactive=True,
|
314 |
+
# )
|
315 |
+
# base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
|
316 |
+
|
317 |
+
# submit_button = gr.Button("Submit Eval")
|
318 |
+
# submission_result = gr.Markdown()
|
319 |
+
# submit_button.click(
|
320 |
+
# add_new_eval,
|
321 |
+
# [
|
322 |
+
# model_name_textbox,
|
323 |
+
# base_model_name_textbox,
|
324 |
+
# revision_name_textbox,
|
325 |
+
# precision,
|
326 |
+
# weight_type,
|
327 |
+
# model_type,
|
328 |
+
# ],
|
329 |
+
# submission_result,
|
330 |
+
# )
|
331 |
|
332 |
with gr.Row():
|
333 |
with gr.Accordion("π Citation", open=False):
|
src/about.py
CHANGED
@@ -19,13 +19,13 @@ NUM_FEWSHOT = 0 # Change with your few shot
|
|
19 |
# ---------------------------------------------------
|
20 |
|
21 |
|
22 |
-
|
23 |
# Your leaderboard name
|
24 |
-
TITLE = """<h1 align="center" id="space-title"
|
25 |
|
26 |
# What does your leaderboard evaluate?
|
27 |
INTRODUCTION_TEXT = """
|
28 |
-
|
|
|
29 |
"""
|
30 |
|
31 |
# Which evaluations are you running? how can people reproduce what you have?
|
|
|
19 |
# ---------------------------------------------------
|
20 |
|
21 |
|
|
|
22 |
# Your leaderboard name
|
23 |
+
TITLE = """<h1 align="center" id="space-title">π
Korean AI leaderboard</h1>"""
|
24 |
|
25 |
# What does your leaderboard evaluate?
|
26 |
INTRODUCTION_TEXT = """
|
27 |
+
[2024 κ΅λ¦½κ΅μ΄μ μΈκ³΅ μ§λ₯ μΈμ΄ λ₯λ ₯ νκ°]
|
28 |
+
- π μΈκ³΅ μ§λ₯, μΈκ°μ κ°μ μ μ΄ν΄νκ³ μ΄μΌκΈ°λ₯Ό μμ±νλ€
|
29 |
"""
|
30 |
|
31 |
# Which evaluations are you running? how can people reproduce what you have?
|