File size: 54,859 Bytes
b0c0df0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"from datasets import load_dataset"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Generating test split: 100%|██████████| 313/313 [00:00<00:00, 324.63 examples/s]\n"
]
}
],
"source": [
"data = load_dataset(\"lmms-lab/LiveBench\", \"2024-09\", split=\"test\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 313/313 [00:25<00:00, 12.06it/s]\n"
]
}
],
"source": [
"from tqdm import tqdm\n",
"\n",
"subsets = {}\n",
"for item in tqdm(data, total=len(data)):\n",
" subset = eval(item[\"website\"])[\"subject\"]\n",
" if subset not in subsets:\n",
" subsets[subset] = 0\n",
" subsets[subset] += 1"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'entertainment': 34,\n",
" 'sports': 44,\n",
" 'technology': 44,\n",
" 'finance': 43,\n",
" 'environment': 31,\n",
" 'politics': 40,\n",
" 'science': 38,\n",
" 'artandculture': 39}"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"subsets"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"34.75"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(subsets.values()) / len(subsets)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"df = data.to_pandas()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"def update(row):\n",
" if row[\"subtask\"] == \"Evaluative Questions\":\n",
" row[\"subtask\"] = \"Divergent Thinking\""
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 None\n",
"1 None\n",
"2 None\n",
"3 None\n",
"4 None\n",
" ... \n",
"308 None\n",
"309 None\n",
"310 None\n",
"311 None\n",
"312 None\n",
"Length: 313, dtype: object"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.apply(update, axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"df = df[df[\"score\"] > 6]"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"251"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(df)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 313/313 [00:00<00:00, 11041.63it/s]\n"
]
}
],
"source": [
"from tqdm import tqdm\n",
"\n",
"subsets = {}\n",
"for idx, item in tqdm(df.iterrows(), total=len(df)):\n",
" subset = eval(item[\"website\"])[\"subject\"]\n",
" if subset not in subsets:\n",
" subsets[subset] = 0\n",
" subsets[subset] += 1"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 312/312 [00:00<00:00, 10684.90it/s]\n"
]
}
],
"source": [
"final_data = {}\n",
"for idx, item in tqdm(df.iterrows(), total=len(df)):\n",
" subtask = item[\"subtask\"]\n",
" if subtask == \"Evaluative Questions\":\n",
" subtask = \"Divergent Thinking\"\n",
" item[\"subtask\"] = subtask\n",
" if subtask not in final_data:\n",
" final_data[subtask] = []\n",
" final_data[subtask].append(item)"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"ename": "KeyError",
"evalue": "'Further Insights'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[39], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mdel\u001b[39;00m \u001b[43mfinal_data\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mFurther Insights\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\n",
"\u001b[0;31mKeyError\u001b[0m: 'Further Insights'"
]
}
],
"source": [
"del final_data[\"Further Insights\"]"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"dict_keys(['Concrete Recognition', 'Analytical Questions', 'Divergent Thinking', 'Real-world Assistance'])"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"final_data.keys()"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [],
"source": [
"from random import shuffle\n",
"\n",
"\n",
"for key, value in final_data.items():\n",
" shuffle(value)\n",
" value = sorted(value, key=lambda x: x[\"score\"])\n",
" value = list(reversed(value))[:50]\n",
" final_data[key] = value"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"final_df = pd.concat([pd.DataFrame(value) for value in final_data.values()])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'entertainment': 34,\n",
" 'sports': 44,\n",
" 'technology': 44,\n",
" 'finance': 43,\n",
" 'environment': 31,\n",
" 'politics': 40,\n",
" 'science': 38,\n",
" 'artandculture': 39}"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"subsets"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 200/200 [00:00<00:00, 11090.61it/s]\n"
]
}
],
"source": [
"from tqdm import tqdm\n",
"\n",
"subsets = {}\n",
"for idx, item in tqdm(final_df.iterrows(), total=len(final_df)):\n",
" subset = item[\"subtask\"]\n",
" if subset not in subsets:\n",
" subsets[subset] = 0\n",
" subsets[subset] += 1"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"200"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(final_df)"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'Concrete Recognition': 50,\n",
" 'Analytical Questions': 50,\n",
" 'Divergent Thinking': 50,\n",
" 'Real-world Assistance': 50}"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"subsets"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"df = df[df[\"subtask\"] != \"Further Insights\"]"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"from datasets import Dataset\n",
"\n",
"new_data = Dataset.from_pandas(final_df, preserve_index=False, features=data.features)"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'id': 41,\n",
" 'images': [<PIL.PngImagePlugin.PngImageFile image mode=RGBA size=1017x1317>],\n",
" 'website': \"{'name': 'technology_3.png', 'subject': 'technology'}\",\n",
" 'question': \"Identify each vulnerability's CVE identifier along with the detailed descriptions provided in the image.\",\n",
" 'answer': \"{'1': {'CVE Identifier': 'CVE-2024-29824', 'Description': 'Ivanti Endpoint Manager (EPM) SQL Injection Vulnerability: Ivanti Endpoint Manager (EPM) contains a SQL injection vulnerability in Core server that allows an unauthenticated attacker within the same network to execute arbitrary code.'}, '2': {'CVE Identifier': 'CVE-2023-25280', 'Description': 'D-Link DIR-820 Router OS Command Injection Vulnerability: D-Link DIR-820 routers contain an OS command injection vulnerability that allows a remote, unauthenticated attacker to escalate privileges to root via a crafted payload with the ping_addr parameter to ping.ccp.'}, '3': {'CVE Identifier': 'CVE-2020-15415', 'Description': 'DrayTek Multiple Vigor Routers OS Command Injection Vulnerability: DrayTek Vigor3900, Vigor2960, and Vigor300B devices contain an OS command injection vulnerability in cgi-bin/mainfunction.cgi/cvmcfgupload that allows for remote code execution via shell metacharacters in a filename when the text/x-python-script content type is used.'}}\",\n",
" 'criteria': \"{'totalScore': 10, 'scoring': {'eachCorrectCVEWithDescription': {'fullMatch': 3.33, 'partialMatch': 1.67, 'missingOrIncorrect': 0}}, 'notes': {'fullMatch': 'The CVE identifier and the associated description are fully correct.', 'partialMatch': 'Either the CVE identifier or the description is correct, but not both.', 'missingOrIncorrect': 'Both the CVE identifier and the description are either incorrect or missing.'}}\",\n",
" 'subtask': 'Concrete Recognition',\n",
" 'data_generator': 'gpt4v',\n",
" 'checker': 'gpt4v',\n",
" 'date_time': '2024-10-07 02:00:15',\n",
" 'screen_shoter': 'human',\n",
" 'screen_size': None,\n",
" 'score': 10,\n",
" 'reason': 'The answer accurately lists all three CVE identifiers mentioned in the image, along with their corresponding products and vendors. The information provided is directly observable in the image and precisely matches the details given for each vulnerability. The response is clear, logically organized, and directly addresses the question asked.',\n",
" 'scorer_name': 'claude'}"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_data[0]"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Dataset({\n",
" features: ['id', 'images', 'website', 'question', 'answer', 'criteria', 'subtask', 'data_generator', 'checker', 'date_time', 'screen_shoter', 'screen_size', 'score', 'reason', 'scorer_name'],\n",
" num_rows: 200\n",
"})"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_data"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Map: 100%|██████████| 200/200 [00:00<00:00, 322.10 examples/s]it/s]\n",
"Creating parquet from Arrow format: 100%|██████████| 2/2 [00:00<00:00, 6.96ba/s]\n",
"Uploading the dataset shards: 100%|██████████| 1/1 [00:10<00:00, 10.69s/it]\n"
]
},
{
"data": {
"text/plain": [
"CommitInfo(commit_url='https://huggingface.co/datasets/lmms-lab/LiveBench/commit/91ed85da9ab4e4eb3babf7c5e39f506a33e62ba1', commit_message='Upload dataset', commit_description='', oid='91ed85da9ab4e4eb3babf7c5e39f506a33e62ba1', pr_url=None, repo_url=RepoUrl('https://huggingface.co/datasets/lmms-lab/LiveBench', endpoint='https://huggingface.co', repo_type='dataset', repo_id='lmms-lab/LiveBench'), pr_revision=None, pr_num=None)"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_data.push_to_hub(\"lmms-lab/LiveBench\", \"2024-09\", split=\"test\")"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Generating test split: 100%|██████████| 200/200 [00:00<00:00, 274.48 examples/s]\n"
]
}
],
"source": [
"new_data = load_dataset(\"lmms-lab/LiveBench\", \"2024-09\", split=\"test\")\n",
"df = new_data.to_pandas()"
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {},
"outputs": [],
"source": [
"def get_subset(row):\n",
" return eval(row)[\"subject\"]\n",
"\n",
"\n",
"df[\"website\"] = df[\"website\"].apply(get_subset)"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'technology'"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[0][\"website\"]"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Map: 100%|██████████| 200/200 [00:00<00:00, 582.27 examples/s]it/s]\n",
"Creating parquet from Arrow format: 100%|██████████| 2/2 [00:00<00:00, 6.05ba/s]\n",
"Uploading the dataset shards: 100%|██████████| 1/1 [00:08<00:00, 8.85s/it]\n"
]
},
{
"data": {
"text/plain": [
"CommitInfo(commit_url='https://huggingface.co/datasets/lmms-lab/LiveBench/commit/c83aaca619b54f3115ea7348139ea0ee6fb139c6', commit_message='Upload dataset', commit_description='', oid='c83aaca619b54f3115ea7348139ea0ee6fb139c6', pr_url=None, repo_url=RepoUrl('https://huggingface.co/datasets/lmms-lab/LiveBench', endpoint='https://huggingface.co', repo_type='dataset', repo_id='lmms-lab/LiveBench'), pr_revision=None, pr_num=None)"
]
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_data = Dataset.from_pandas(df, preserve_index=False, features=new_data.features)\n",
"new_data.push_to_hub(\"lmms-lab/LiveBench\", \"2024-09\", split=\"test\")"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Generating train split: 200 examples [00:01, 132.53 examples/s]\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/PIL/ImageFile.py:547\u001b[0m, in \u001b[0;36m_save\u001b[0;34m(im, fp, tile, bufsize)\u001b[0m\n\u001b[1;32m 546\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 547\u001b[0m fh \u001b[38;5;241m=\u001b[39m \u001b[43mfp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfileno\u001b[49m()\n\u001b[1;32m 548\u001b[0m fp\u001b[38;5;241m.\u001b[39mflush()\n",
"\u001b[0;31mAttributeError\u001b[0m: '_idat' object has no attribute 'fileno'",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[58], line 15\u001b[0m\n\u001b[1;32m 12\u001b[0m new_item[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mimages\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m [image]\n\u001b[1;32m 13\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m new_item\n\u001b[0;32m---> 15\u001b[0m dataset \u001b[38;5;241m=\u001b[39m \u001b[43mDataset\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_generator\u001b[49m\u001b[43m(\u001b[49m\u001b[43mget_data\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/arrow_dataset.py:1099\u001b[0m, in \u001b[0;36mDataset.from_generator\u001b[0;34m(generator, features, cache_dir, keep_in_memory, gen_kwargs, num_proc, split, **kwargs)\u001b[0m\n\u001b[1;32m 1037\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Create a Dataset from a generator.\u001b[39;00m\n\u001b[1;32m 1038\u001b[0m \n\u001b[1;32m 1039\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1086\u001b[0m \u001b[38;5;124;03m```\u001b[39;00m\n\u001b[1;32m 1087\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 1088\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mio\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgenerator\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m GeneratorDatasetInputStream\n\u001b[1;32m 1090\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mGeneratorDatasetInputStream\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1091\u001b[0m \u001b[43m \u001b[49m\u001b[43mgenerator\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgenerator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1092\u001b[0m \u001b[43m \u001b[49m\u001b[43mfeatures\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfeatures\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1093\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1094\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeep_in_memory\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_in_memory\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1095\u001b[0m \u001b[43m \u001b[49m\u001b[43mgen_kwargs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgen_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1096\u001b[0m \u001b[43m \u001b[49m\u001b[43mnum_proc\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnum_proc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1097\u001b[0m \u001b[43m \u001b[49m\u001b[43msplit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msplit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1098\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m-> 1099\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/io/generator.py:49\u001b[0m, in \u001b[0;36mGeneratorDatasetInputStream.read\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 46\u001b[0m verification_mode \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 47\u001b[0m base_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m---> 49\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbuilder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdownload_and_prepare\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 50\u001b[0m \u001b[43m \u001b[49m\u001b[43mdownload_config\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdownload_config\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 51\u001b[0m \u001b[43m \u001b[49m\u001b[43mdownload_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdownload_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 52\u001b[0m \u001b[43m \u001b[49m\u001b[43mverification_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mverification_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 53\u001b[0m \u001b[43m \u001b[49m\u001b[43mbase_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbase_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 54\u001b[0m \u001b[43m \u001b[49m\u001b[43mnum_proc\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnum_proc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 55\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 56\u001b[0m dataset \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuilder\u001b[38;5;241m.\u001b[39mas_dataset(\n\u001b[1;32m 57\u001b[0m split\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuilder\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39msplit, verification_mode\u001b[38;5;241m=\u001b[39mverification_mode, in_memory\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkeep_in_memory\n\u001b[1;32m 58\u001b[0m )\n\u001b[1;32m 59\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m dataset\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/builder.py:924\u001b[0m, in \u001b[0;36mDatasetBuilder.download_and_prepare\u001b[0;34m(self, output_dir, download_config, download_mode, verification_mode, dl_manager, base_path, file_format, max_shard_size, num_proc, storage_options, **download_and_prepare_kwargs)\u001b[0m\n\u001b[1;32m 922\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m num_proc \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 923\u001b[0m prepare_split_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnum_proc\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m num_proc\n\u001b[0;32m--> 924\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_download_and_prepare\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 925\u001b[0m \u001b[43m \u001b[49m\u001b[43mdl_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdl_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 926\u001b[0m \u001b[43m \u001b[49m\u001b[43mverification_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mverification_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 927\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mprepare_split_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 928\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mdownload_and_prepare_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 929\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 930\u001b[0m \u001b[38;5;66;03m# Sync info\u001b[39;00m\n\u001b[1;32m 931\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minfo\u001b[38;5;241m.\u001b[39mdataset_size \u001b[38;5;241m=\u001b[39m \u001b[38;5;28msum\u001b[39m(split\u001b[38;5;241m.\u001b[39mnum_bytes \u001b[38;5;28;01mfor\u001b[39;00m split \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minfo\u001b[38;5;241m.\u001b[39msplits\u001b[38;5;241m.\u001b[39mvalues())\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/builder.py:1647\u001b[0m, in \u001b[0;36mGeneratorBasedBuilder._download_and_prepare\u001b[0;34m(self, dl_manager, verification_mode, **prepare_splits_kwargs)\u001b[0m\n\u001b[1;32m 1646\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_download_and_prepare\u001b[39m(\u001b[38;5;28mself\u001b[39m, dl_manager, verification_mode, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mprepare_splits_kwargs):\n\u001b[0;32m-> 1647\u001b[0m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_download_and_prepare\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1648\u001b[0m \u001b[43m \u001b[49m\u001b[43mdl_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1649\u001b[0m \u001b[43m \u001b[49m\u001b[43mverification_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1650\u001b[0m \u001b[43m \u001b[49m\u001b[43mcheck_duplicate_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mverification_mode\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m==\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mVerificationMode\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mBASIC_CHECKS\u001b[49m\n\u001b[1;32m 1651\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mverification_mode\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m==\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mVerificationMode\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mALL_CHECKS\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1652\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mprepare_splits_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1653\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/builder.py:999\u001b[0m, in \u001b[0;36mDatasetBuilder._download_and_prepare\u001b[0;34m(self, dl_manager, verification_mode, **prepare_split_kwargs)\u001b[0m\n\u001b[1;32m 995\u001b[0m split_dict\u001b[38;5;241m.\u001b[39madd(split_generator\u001b[38;5;241m.\u001b[39msplit_info)\n\u001b[1;32m 997\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 998\u001b[0m \u001b[38;5;66;03m# Prepare split will record examples associated to the split\u001b[39;00m\n\u001b[0;32m--> 999\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_prepare_split\u001b[49m\u001b[43m(\u001b[49m\u001b[43msplit_generator\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mprepare_split_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1000\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mOSError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 1001\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mOSError\u001b[39;00m(\n\u001b[1;32m 1002\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCannot find data file. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1003\u001b[0m \u001b[38;5;241m+\u001b[39m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmanual_download_instructions \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 1004\u001b[0m \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mOriginal error:\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1005\u001b[0m \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mstr\u001b[39m(e)\n\u001b[1;32m 1006\u001b[0m ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/builder.py:1485\u001b[0m, in \u001b[0;36mGeneratorBasedBuilder._prepare_split\u001b[0;34m(self, split_generator, check_duplicate_keys, file_format, num_proc, max_shard_size)\u001b[0m\n\u001b[1;32m 1483\u001b[0m job_id \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n\u001b[1;32m 1484\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m pbar:\n\u001b[0;32m-> 1485\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mjob_id\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdone\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcontent\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_prepare_split_single\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1486\u001b[0m \u001b[43m \u001b[49m\u001b[43mgen_kwargs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgen_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mjob_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mjob_id\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m_prepare_split_args\u001b[49m\n\u001b[1;32m 1487\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m 1488\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mdone\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m 1489\u001b[0m \u001b[43m \u001b[49m\u001b[43mresult\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mcontent\u001b[49m\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/builder.py:1633\u001b[0m, in \u001b[0;36mGeneratorBasedBuilder._prepare_split_single\u001b[0;34m(self, gen_kwargs, fpath, file_format, max_shard_size, split_info, check_duplicate_keys, job_id)\u001b[0m\n\u001b[1;32m 1631\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m job_id, \u001b[38;5;28;01mFalse\u001b[39;00m, num_examples_progress_update\n\u001b[1;32m 1632\u001b[0m num_shards \u001b[38;5;241m=\u001b[39m shard_id \u001b[38;5;241m+\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m-> 1633\u001b[0m num_examples, num_bytes \u001b[38;5;241m=\u001b[39m \u001b[43mwriter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfinalize\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1634\u001b[0m writer\u001b[38;5;241m.\u001b[39mclose()\n\u001b[1;32m 1635\u001b[0m shard_lengths\u001b[38;5;241m.\u001b[39mappend(num_examples)\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/arrow_writer.py:594\u001b[0m, in \u001b[0;36mArrowWriter.finalize\u001b[0;34m(self, close_stream)\u001b[0m\n\u001b[1;32m 592\u001b[0m \u001b[38;5;66;03m# Re-intializing to empty list for next batch\u001b[39;00m\n\u001b[1;32m 593\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhkey_record \u001b[38;5;241m=\u001b[39m []\n\u001b[0;32m--> 594\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mwrite_examples_on_file\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 595\u001b[0m \u001b[38;5;66;03m# If schema is known, infer features even if no examples were written\u001b[39;00m\n\u001b[1;32m 596\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpa_writer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mschema:\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/arrow_writer.py:453\u001b[0m, in \u001b[0;36mArrowWriter.write_examples_on_file\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 448\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 449\u001b[0m batch_examples[col] \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m 450\u001b[0m row[\u001b[38;5;241m0\u001b[39m][col]\u001b[38;5;241m.\u001b[39mto_pylist()[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(row[\u001b[38;5;241m0\u001b[39m][col], (pa\u001b[38;5;241m.\u001b[39mArray, pa\u001b[38;5;241m.\u001b[39mChunkedArray)) \u001b[38;5;28;01melse\u001b[39;00m row[\u001b[38;5;241m0\u001b[39m][col]\n\u001b[1;32m 451\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m row \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcurrent_examples\n\u001b[1;32m 452\u001b[0m ]\n\u001b[0;32m--> 453\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mwrite_batch\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbatch_examples\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbatch_examples\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 454\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcurrent_examples \u001b[38;5;241m=\u001b[39m []\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/arrow_writer.py:563\u001b[0m, in \u001b[0;36mArrowWriter.write_batch\u001b[0;34m(self, batch_examples, writer_batch_size)\u001b[0m\n\u001b[1;32m 561\u001b[0m col_try_type \u001b[38;5;241m=\u001b[39m try_features[col] \u001b[38;5;28;01mif\u001b[39;00m try_features \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m col \u001b[38;5;129;01min\u001b[39;00m try_features \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 562\u001b[0m typed_sequence \u001b[38;5;241m=\u001b[39m OptimizedTypedSequence(col_values, \u001b[38;5;28mtype\u001b[39m\u001b[38;5;241m=\u001b[39mcol_type, try_type\u001b[38;5;241m=\u001b[39mcol_try_type, col\u001b[38;5;241m=\u001b[39mcol)\n\u001b[0;32m--> 563\u001b[0m arrays\u001b[38;5;241m.\u001b[39mappend(\u001b[43mpa\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtyped_sequence\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m 564\u001b[0m inferred_features[col] \u001b[38;5;241m=\u001b[39m typed_sequence\u001b[38;5;241m.\u001b[39mget_inferred_type()\n\u001b[1;32m 565\u001b[0m schema \u001b[38;5;241m=\u001b[39m inferred_features\u001b[38;5;241m.\u001b[39marrow_schema \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpa_writer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mschema\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/pyarrow/array.pxi:248\u001b[0m, in \u001b[0;36mpyarrow.lib.array\u001b[0;34m()\u001b[0m\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/pyarrow/array.pxi:112\u001b[0m, in \u001b[0;36mpyarrow.lib._handle_arrow_array_protocol\u001b[0;34m()\u001b[0m\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/arrow_writer.py:188\u001b[0m, in \u001b[0;36mTypedSequence.__arrow_array__\u001b[0;34m(self, type)\u001b[0m\n\u001b[1;32m 186\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 187\u001b[0m trying_cast_to_python_objects \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[0;32m--> 188\u001b[0m out \u001b[38;5;241m=\u001b[39m pa\u001b[38;5;241m.\u001b[39marray(\u001b[43mcast_to_python_objects\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43monly_1d_for_numpy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m)\n\u001b[1;32m 189\u001b[0m \u001b[38;5;66;03m# use smaller integer precisions if possible\u001b[39;00m\n\u001b[1;32m 190\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrying_int_optimization:\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/features/features.py:455\u001b[0m, in \u001b[0;36mcast_to_python_objects\u001b[0;34m(obj, only_1d_for_numpy, optimize_list_casting)\u001b[0m\n\u001b[1;32m 435\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcast_to_python_objects\u001b[39m(obj: Any, only_1d_for_numpy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, optimize_list_casting\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[1;32m 436\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 437\u001b[0m \u001b[38;5;124;03m Cast numpy/pytorch/tensorflow/pandas objects to python lists.\u001b[39;00m\n\u001b[1;32m 438\u001b[0m \u001b[38;5;124;03m It works recursively.\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 453\u001b[0m \u001b[38;5;124;03m casted_obj: the casted object\u001b[39;00m\n\u001b[1;32m 454\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 455\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_cast_to_python_objects\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 456\u001b[0m \u001b[43m \u001b[49m\u001b[43mobj\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43monly_1d_for_numpy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43monly_1d_for_numpy\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43moptimize_list_casting\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptimize_list_casting\u001b[49m\n\u001b[1;32m 457\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;241m0\u001b[39m]\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/features/features.py:417\u001b[0m, in \u001b[0;36m_cast_to_python_objects\u001b[0;34m(obj, only_1d_for_numpy, optimize_list_casting)\u001b[0m\n\u001b[1;32m 411\u001b[0m casted_first_elmt, has_changed_first_elmt \u001b[38;5;241m=\u001b[39m _cast_to_python_objects(\n\u001b[1;32m 412\u001b[0m first_elmt, only_1d_for_numpy\u001b[38;5;241m=\u001b[39monly_1d_for_numpy, optimize_list_casting\u001b[38;5;241m=\u001b[39moptimize_list_casting\n\u001b[1;32m 413\u001b[0m )\n\u001b[1;32m 414\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m has_changed_first_elmt \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m optimize_list_casting:\n\u001b[1;32m 415\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m (\n\u001b[1;32m 416\u001b[0m [\n\u001b[0;32m--> 417\u001b[0m \u001b[43m_cast_to_python_objects\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 418\u001b[0m \u001b[43m \u001b[49m\u001b[43melmt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43monly_1d_for_numpy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43monly_1d_for_numpy\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43moptimize_list_casting\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptimize_list_casting\u001b[49m\n\u001b[1;32m 419\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m 420\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m elmt \u001b[38;5;129;01min\u001b[39;00m obj\n\u001b[1;32m 421\u001b[0m ],\n\u001b[1;32m 422\u001b[0m \u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 423\u001b[0m )\n\u001b[1;32m 424\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 425\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(obj, (\u001b[38;5;28mlist\u001b[39m, \u001b[38;5;28mtuple\u001b[39m)):\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/features/features.py:411\u001b[0m, in \u001b[0;36m_cast_to_python_objects\u001b[0;34m(obj, only_1d_for_numpy, optimize_list_casting)\u001b[0m\n\u001b[1;32m 409\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m _check_non_null_non_empty_recursive(first_elmt):\n\u001b[1;32m 410\u001b[0m \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[0;32m--> 411\u001b[0m casted_first_elmt, has_changed_first_elmt \u001b[38;5;241m=\u001b[39m \u001b[43m_cast_to_python_objects\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 412\u001b[0m \u001b[43m \u001b[49m\u001b[43mfirst_elmt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43monly_1d_for_numpy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43monly_1d_for_numpy\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43moptimize_list_casting\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptimize_list_casting\u001b[49m\n\u001b[1;32m 413\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 414\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m has_changed_first_elmt \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m optimize_list_casting:\n\u001b[1;32m 415\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m (\n\u001b[1;32m 416\u001b[0m [\n\u001b[1;32m 417\u001b[0m _cast_to_python_objects(\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 422\u001b[0m \u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 423\u001b[0m )\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/features/features.py:367\u001b[0m, in \u001b[0;36m_cast_to_python_objects\u001b[0;34m(obj, only_1d_for_numpy, optimize_list_casting)\u001b[0m\n\u001b[1;32m 357\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m (\n\u001b[1;32m 358\u001b[0m [\n\u001b[1;32m 359\u001b[0m _cast_to_python_objects(\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 364\u001b[0m \u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 365\u001b[0m )\n\u001b[1;32m 366\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m config\u001b[38;5;241m.\u001b[39mPIL_AVAILABLE \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPIL\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m sys\u001b[38;5;241m.\u001b[39mmodules \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(obj, PIL\u001b[38;5;241m.\u001b[39mImage\u001b[38;5;241m.\u001b[39mImage):\n\u001b[0;32m--> 367\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mencode_pil_image\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m)\u001b[49m, \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 368\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(obj, pd\u001b[38;5;241m.\u001b[39mSeries):\n\u001b[1;32m 369\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m (\n\u001b[1;32m 370\u001b[0m _cast_to_python_objects(\n\u001b[1;32m 371\u001b[0m obj\u001b[38;5;241m.\u001b[39mtolist(), only_1d_for_numpy\u001b[38;5;241m=\u001b[39monly_1d_for_numpy, optimize_list_casting\u001b[38;5;241m=\u001b[39moptimize_list_casting\n\u001b[1;32m 372\u001b[0m )[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 373\u001b[0m \u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 374\u001b[0m )\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/features/image.py:315\u001b[0m, in \u001b[0;36mencode_pil_image\u001b[0;34m(image)\u001b[0m\n\u001b[1;32m 313\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpath\u001b[39m\u001b[38;5;124m\"\u001b[39m: image\u001b[38;5;241m.\u001b[39mfilename, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbytes\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28;01mNone\u001b[39;00m}\n\u001b[1;32m 314\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 315\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpath\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbytes\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[43mimage_to_bytes\u001b[49m\u001b[43m(\u001b[49m\u001b[43mimage\u001b[49m\u001b[43m)\u001b[49m}\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/datasets/features/image.py:307\u001b[0m, in \u001b[0;36mimage_to_bytes\u001b[0;34m(image)\u001b[0m\n\u001b[1;32m 305\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 306\u001b[0m \u001b[38;5;28mformat\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPNG\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m image\u001b[38;5;241m.\u001b[39mmode \u001b[38;5;129;01min\u001b[39;00m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m1\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mL\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLA\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRGB\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRGBA\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTIFF\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 307\u001b[0m \u001b[43mimage\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msave\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mformat\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mformat\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 308\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m buffer\u001b[38;5;241m.\u001b[39mgetvalue()\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/PIL/Image.py:2568\u001b[0m, in \u001b[0;36mImage.save\u001b[0;34m(self, fp, format, **params)\u001b[0m\n\u001b[1;32m 2565\u001b[0m fp \u001b[38;5;241m=\u001b[39m cast(IO[\u001b[38;5;28mbytes\u001b[39m], fp)\n\u001b[1;32m 2567\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 2568\u001b[0m \u001b[43msave_handler\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfp\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2569\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[1;32m 2570\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m open_fp:\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/PIL/PngImagePlugin.py:1431\u001b[0m, in \u001b[0;36m_save\u001b[0;34m(im, fp, filename, chunk, save_all)\u001b[0m\n\u001b[1;32m 1427\u001b[0m im \u001b[38;5;241m=\u001b[39m _write_multiple_frames(\n\u001b[1;32m 1428\u001b[0m im, fp, chunk, mode, rawmode, default_image, append_images\n\u001b[1;32m 1429\u001b[0m )\n\u001b[1;32m 1430\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m im:\n\u001b[0;32m-> 1431\u001b[0m \u001b[43mImageFile\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_save\u001b[49m\u001b[43m(\u001b[49m\u001b[43mim\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_idat\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfp\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mzip\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mim\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msize\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrawmode\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1433\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m info:\n\u001b[1;32m 1434\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m info_chunk \u001b[38;5;129;01min\u001b[39;00m info\u001b[38;5;241m.\u001b[39mchunks:\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/PIL/ImageFile.py:551\u001b[0m, in \u001b[0;36m_save\u001b[0;34m(im, fp, tile, bufsize)\u001b[0m\n\u001b[1;32m 549\u001b[0m _encode_tile(im, fp, tile, bufsize, fh)\n\u001b[1;32m 550\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mAttributeError\u001b[39;00m, io\u001b[38;5;241m.\u001b[39mUnsupportedOperation) \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[0;32m--> 551\u001b[0m \u001b[43m_encode_tile\u001b[49m\u001b[43m(\u001b[49m\u001b[43mim\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfp\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtile\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbufsize\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mexc\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 552\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(fp, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mflush\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 553\u001b[0m fp\u001b[38;5;241m.\u001b[39mflush()\n",
"File \u001b[0;32m/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/PIL/ImageFile.py:570\u001b[0m, in \u001b[0;36m_encode_tile\u001b[0;34m(im, fp, tile, bufsize, fh, exc)\u001b[0m\n\u001b[1;32m 567\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m exc:\n\u001b[1;32m 568\u001b[0m \u001b[38;5;66;03m# compress to Python file-compatible object\u001b[39;00m\n\u001b[1;32m 569\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 570\u001b[0m errcode, data \u001b[38;5;241m=\u001b[39m \u001b[43mencoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbufsize\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;241m1\u001b[39m:]\n\u001b[1;32m 571\u001b[0m fp\u001b[38;5;241m.\u001b[39mwrite(data)\n\u001b[1;32m 572\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m errcode:\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"from PIL import Image\n",
"import io\n",
"\n",
"\n",
"def get_data():\n",
" for index, item in df.iterrows():\n",
" new_item = item.to_dict()\n",
" new_item[\"subset\"] = eval(item[\"website\"])[\"subject\"]\n",
" del new_item[\"website\"]\n",
" new_item[\"id\"] = index\n",
" image_bytes = new_item[\"images\"][0][\"bytes\"]\n",
" image = Image.open(io.BytesIO(image_bytes))\n",
" new_item[\"images\"] = [image]\n",
" yield new_item\n",
"\n",
"\n",
"dataset = Dataset.from_generator(get_data)"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Creating parquet from Arrow format: 100%|██████████| 2/2 [00:00<00:00, 3.93ba/s]\n",
"Uploading the dataset shards: 100%|██████████| 1/1 [00:16<00:00, 16.91s/it]\n"
]
},
{
"data": {
"text/plain": [
"CommitInfo(commit_url='https://huggingface.co/datasets/lmms-lab/LiveBench/commit/a25ad8c1a882b28a838d6ca3afd26cd29beac153', commit_message='Upload dataset', commit_description='', oid='a25ad8c1a882b28a838d6ca3afd26cd29beac153', pr_url=None, repo_url=RepoUrl('https://huggingface.co/datasets/lmms-lab/LiveBench', endpoint='https://huggingface.co', repo_type='dataset', repo_id='lmms-lab/LiveBench'), pr_revision=None, pr_num=None)"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset.push_to_hub(\"lmms-lab/LiveBench\", \"2024-09\", split=\"test\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "live_bench",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|