Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Separate submission section
Browse files
app.py
CHANGED
|
@@ -389,6 +389,113 @@ with gr.Blocks() as demo_leaderboard:
|
|
| 389 |
)
|
| 390 |
|
| 391 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 392 |
with gr.Blocks(css=custom_css) as demo:
|
| 393 |
gr.HTML(TITLE)
|
| 394 |
gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
|
|
@@ -401,110 +508,7 @@ with gr.Blocks(css=custom_css) as demo:
|
|
| 401 |
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
| 402 |
|
| 403 |
with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
|
| 404 |
-
|
| 405 |
-
with gr.Row():
|
| 406 |
-
gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
|
| 407 |
-
|
| 408 |
-
with gr.Column():
|
| 409 |
-
with gr.Accordion(
|
| 410 |
-
f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
|
| 411 |
-
open=False,
|
| 412 |
-
):
|
| 413 |
-
with gr.Row():
|
| 414 |
-
finished_eval_table = gr.components.Dataframe(
|
| 415 |
-
value=finished_eval_queue_df,
|
| 416 |
-
headers=EVAL_COLS,
|
| 417 |
-
datatype=EVAL_TYPES,
|
| 418 |
-
row_count=5,
|
| 419 |
-
)
|
| 420 |
-
with gr.Accordion(
|
| 421 |
-
f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
|
| 422 |
-
open=False,
|
| 423 |
-
):
|
| 424 |
-
with gr.Row():
|
| 425 |
-
running_eval_table = gr.components.Dataframe(
|
| 426 |
-
value=running_eval_queue_df,
|
| 427 |
-
headers=EVAL_COLS,
|
| 428 |
-
datatype=EVAL_TYPES,
|
| 429 |
-
row_count=5,
|
| 430 |
-
)
|
| 431 |
-
|
| 432 |
-
with gr.Accordion(
|
| 433 |
-
f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
|
| 434 |
-
open=False,
|
| 435 |
-
):
|
| 436 |
-
with gr.Row():
|
| 437 |
-
pending_eval_table = gr.components.Dataframe(
|
| 438 |
-
value=pending_eval_queue_df,
|
| 439 |
-
headers=EVAL_COLS,
|
| 440 |
-
datatype=EVAL_TYPES,
|
| 441 |
-
row_count=5,
|
| 442 |
-
)
|
| 443 |
-
with gr.Accordion(
|
| 444 |
-
f"❎ Failed Evaluation Queue ({len(failed_eval_queue_df)})",
|
| 445 |
-
open=False,
|
| 446 |
-
):
|
| 447 |
-
with gr.Row():
|
| 448 |
-
failed_eval_table = gr.components.Dataframe(
|
| 449 |
-
value=failed_eval_queue_df,
|
| 450 |
-
headers=EVAL_COLS,
|
| 451 |
-
datatype=EVAL_TYPES,
|
| 452 |
-
row_count=5,
|
| 453 |
-
)
|
| 454 |
-
with gr.Row():
|
| 455 |
-
gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
|
| 456 |
-
|
| 457 |
-
with gr.Row():
|
| 458 |
-
with gr.Column():
|
| 459 |
-
model_name_textbox = gr.Textbox(label="Model name")
|
| 460 |
-
revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
|
| 461 |
-
model_type = gr.Dropdown(
|
| 462 |
-
choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
|
| 463 |
-
label="Model type",
|
| 464 |
-
multiselect=False,
|
| 465 |
-
value=None,
|
| 466 |
-
interactive=True,
|
| 467 |
-
)
|
| 468 |
-
|
| 469 |
-
with gr.Column():
|
| 470 |
-
precision = gr.Dropdown(
|
| 471 |
-
choices=[i.value.name for i in Precision if i != Precision.Unknown],
|
| 472 |
-
label="Precision",
|
| 473 |
-
multiselect=False,
|
| 474 |
-
value="float16",
|
| 475 |
-
interactive=True,
|
| 476 |
-
)
|
| 477 |
-
weight_type = gr.Dropdown(
|
| 478 |
-
choices=[i.value.name for i in WeightType],
|
| 479 |
-
label="Weights type",
|
| 480 |
-
multiselect=False,
|
| 481 |
-
value="Original",
|
| 482 |
-
interactive=True,
|
| 483 |
-
)
|
| 484 |
-
base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
|
| 485 |
-
add_special_tokens = gr.Dropdown(
|
| 486 |
-
choices=[i.value.name for i in AddSpecialTokens if i != AddSpecialTokens.Unknown],
|
| 487 |
-
label="AddSpecialTokens",
|
| 488 |
-
multiselect=False,
|
| 489 |
-
value="False",
|
| 490 |
-
interactive=True,
|
| 491 |
-
)
|
| 492 |
-
|
| 493 |
-
submit_button = gr.Button("Submit Eval")
|
| 494 |
-
submission_result = gr.Markdown()
|
| 495 |
-
submit_button.click(
|
| 496 |
-
add_new_eval,
|
| 497 |
-
[
|
| 498 |
-
model_name_textbox,
|
| 499 |
-
base_model_name_textbox,
|
| 500 |
-
revision_name_textbox,
|
| 501 |
-
precision,
|
| 502 |
-
weight_type,
|
| 503 |
-
model_type,
|
| 504 |
-
add_special_tokens,
|
| 505 |
-
],
|
| 506 |
-
submission_result,
|
| 507 |
-
)
|
| 508 |
|
| 509 |
with gr.Row():
|
| 510 |
with gr.Accordion("📙 Citation", open=False):
|
|
|
|
| 389 |
)
|
| 390 |
|
| 391 |
|
| 392 |
+
with gr.Blocks() as demo_submission:
|
| 393 |
+
with gr.Column():
|
| 394 |
+
with gr.Row():
|
| 395 |
+
gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
|
| 396 |
+
|
| 397 |
+
with gr.Column():
|
| 398 |
+
with gr.Accordion(
|
| 399 |
+
f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
|
| 400 |
+
open=False,
|
| 401 |
+
):
|
| 402 |
+
with gr.Row():
|
| 403 |
+
finished_eval_table = gr.components.Dataframe(
|
| 404 |
+
value=finished_eval_queue_df,
|
| 405 |
+
headers=EVAL_COLS,
|
| 406 |
+
datatype=EVAL_TYPES,
|
| 407 |
+
row_count=5,
|
| 408 |
+
)
|
| 409 |
+
with gr.Accordion(
|
| 410 |
+
f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
|
| 411 |
+
open=False,
|
| 412 |
+
):
|
| 413 |
+
with gr.Row():
|
| 414 |
+
running_eval_table = gr.components.Dataframe(
|
| 415 |
+
value=running_eval_queue_df,
|
| 416 |
+
headers=EVAL_COLS,
|
| 417 |
+
datatype=EVAL_TYPES,
|
| 418 |
+
row_count=5,
|
| 419 |
+
)
|
| 420 |
+
|
| 421 |
+
with gr.Accordion(
|
| 422 |
+
f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
|
| 423 |
+
open=False,
|
| 424 |
+
):
|
| 425 |
+
with gr.Row():
|
| 426 |
+
pending_eval_table = gr.components.Dataframe(
|
| 427 |
+
value=pending_eval_queue_df,
|
| 428 |
+
headers=EVAL_COLS,
|
| 429 |
+
datatype=EVAL_TYPES,
|
| 430 |
+
row_count=5,
|
| 431 |
+
)
|
| 432 |
+
with gr.Accordion(
|
| 433 |
+
f"❎ Failed Evaluation Queue ({len(failed_eval_queue_df)})",
|
| 434 |
+
open=False,
|
| 435 |
+
):
|
| 436 |
+
with gr.Row():
|
| 437 |
+
failed_eval_table = gr.components.Dataframe(
|
| 438 |
+
value=failed_eval_queue_df,
|
| 439 |
+
headers=EVAL_COLS,
|
| 440 |
+
datatype=EVAL_TYPES,
|
| 441 |
+
row_count=5,
|
| 442 |
+
)
|
| 443 |
+
with gr.Row():
|
| 444 |
+
gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
|
| 445 |
+
|
| 446 |
+
with gr.Row():
|
| 447 |
+
with gr.Column():
|
| 448 |
+
model_name_textbox = gr.Textbox(label="Model name")
|
| 449 |
+
revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
|
| 450 |
+
model_type = gr.Dropdown(
|
| 451 |
+
choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
|
| 452 |
+
label="Model type",
|
| 453 |
+
multiselect=False,
|
| 454 |
+
value=None,
|
| 455 |
+
interactive=True,
|
| 456 |
+
)
|
| 457 |
+
|
| 458 |
+
with gr.Column():
|
| 459 |
+
precision = gr.Dropdown(
|
| 460 |
+
choices=[i.value.name for i in Precision if i != Precision.Unknown],
|
| 461 |
+
label="Precision",
|
| 462 |
+
multiselect=False,
|
| 463 |
+
value="float16",
|
| 464 |
+
interactive=True,
|
| 465 |
+
)
|
| 466 |
+
weight_type = gr.Dropdown(
|
| 467 |
+
choices=[i.value.name for i in WeightType],
|
| 468 |
+
label="Weights type",
|
| 469 |
+
multiselect=False,
|
| 470 |
+
value="Original",
|
| 471 |
+
interactive=True,
|
| 472 |
+
)
|
| 473 |
+
base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
|
| 474 |
+
add_special_tokens = gr.Dropdown(
|
| 475 |
+
choices=[i.value.name for i in AddSpecialTokens if i != AddSpecialTokens.Unknown],
|
| 476 |
+
label="AddSpecialTokens",
|
| 477 |
+
multiselect=False,
|
| 478 |
+
value="False",
|
| 479 |
+
interactive=True,
|
| 480 |
+
)
|
| 481 |
+
|
| 482 |
+
submit_button = gr.Button("Submit Eval")
|
| 483 |
+
submission_result = gr.Markdown()
|
| 484 |
+
submit_button.click(
|
| 485 |
+
add_new_eval,
|
| 486 |
+
[
|
| 487 |
+
model_name_textbox,
|
| 488 |
+
base_model_name_textbox,
|
| 489 |
+
revision_name_textbox,
|
| 490 |
+
precision,
|
| 491 |
+
weight_type,
|
| 492 |
+
model_type,
|
| 493 |
+
add_special_tokens,
|
| 494 |
+
],
|
| 495 |
+
submission_result,
|
| 496 |
+
)
|
| 497 |
+
|
| 498 |
+
|
| 499 |
with gr.Blocks(css=custom_css) as demo:
|
| 500 |
gr.HTML(TITLE)
|
| 501 |
gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
|
|
|
|
| 508 |
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
| 509 |
|
| 510 |
with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
|
| 511 |
+
demo_submission.render()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 512 |
|
| 513 |
with gr.Row():
|
| 514 |
with gr.Accordion("📙 Citation", open=False):
|