Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +228 -0
- 14B_AgiBot_post-train/iter_000050000/model/__100_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__101_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__102_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__103_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__104_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__105_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__106_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__107_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__108_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__109_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__110_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__111_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__112_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__113_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__114_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__115_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__116_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__117_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__118_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__119_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__120_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__121_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__122_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__123_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__124_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__125_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__126_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__127_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__128_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__129_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__130_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__131_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__132_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__133_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__134_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__135_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__136_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__137_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__138_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__139_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__140_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__141_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__142_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__143_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__144_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__145_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__146_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__147_0.distcp +0 -0
- 14B_AgiBot_post-train/iter_000050000/model/__148_0.distcp +0 -0
.gitattributes
CHANGED
|
@@ -453,3 +453,231 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 453 |
14B_YAM_post-train_5k/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 454 |
14B_YAM_post-train_5k/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 455 |
14B_YAM_post-train_5k/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 453 |
14B_YAM_post-train_5k/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 454 |
14B_YAM_post-train_5k/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 455 |
14B_YAM_post-train_5k/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 456 |
+
14B_AgiBot_post-train/iter_000050000/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 457 |
+
2B_YAM_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 458 |
+
2B_YAM_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 459 |
+
2B_AgiBot_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 460 |
+
2B_YAM_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 461 |
+
2B_YAM_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 462 |
+
2B_YAM_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 463 |
+
2B_YAM_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 464 |
+
2B_YAM_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 465 |
+
2B_YAM_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 466 |
+
2B_YAM_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 467 |
+
2B_YAM_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 468 |
+
2B_AgiBot_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 469 |
+
2B_AgiBot_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 470 |
+
2B_AgiBot_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 471 |
+
2B_AgiBot_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 472 |
+
2B_AgiBot_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 473 |
+
2B_AgiBot_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 474 |
+
2B_AgiBot_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 475 |
+
2B_AgiBot_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 476 |
+
2B_AgiBot_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 477 |
+
2B_YAM_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 478 |
+
2B_YAM_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 479 |
+
2B_YAM_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 480 |
+
2B_YAM_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 481 |
+
14B_GR1_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 482 |
+
2B_YAM_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 483 |
+
2B_YAM_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 484 |
+
2B_YAM_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 485 |
+
2B_YAM_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 486 |
+
2B_AgiBot_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 487 |
+
2B_AgiBot_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 488 |
+
2B_AgiBot_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 489 |
+
2B_AgiBot_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 490 |
+
2B_AgiBot_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 491 |
+
2B_AgiBot_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 492 |
+
2B_AgiBot_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 493 |
+
2B_AgiBot_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 494 |
+
14B_GR1_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 495 |
+
14B_GR1_post-train/iter_000050000/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 496 |
+
14B_GR1_post-train/iter_000050000/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 497 |
+
14B_GR1_post-train/iter_000050000/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 498 |
+
14B_GR1_post-train/iter_000050000/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 499 |
+
14B_GR1_post-train/iter_000050000/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 500 |
+
14B_GR1_post-train/iter_000050000/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 501 |
+
14B_GR1_post-train/iter_000050000/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 502 |
+
14B_GR1_post-train/iter_000050000/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 503 |
+
14B_GR1_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 504 |
+
14B_GR1_post-train/iter_000050000/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 505 |
+
14B_GR1_post-train/iter_000050000/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 506 |
+
14B_GR1_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 507 |
+
14B_GR1_post-train/iter_000050000/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 508 |
+
14B_GR1_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 509 |
+
14B_GR1_post-train/iter_000050000/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 510 |
+
14B_GR1_post-train/iter_000050000/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 511 |
+
14B_GR1_post-train/iter_000050000/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 512 |
+
14B_GR1_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 513 |
+
14B_GR1_post-train/iter_000050000/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 514 |
+
14B_GR1_post-train/iter_000050000/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 515 |
+
14B_GR1_post-train/iter_000050000/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 516 |
+
14B_GR1_post-train/iter_000050000/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 517 |
+
14B_GR1_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 518 |
+
14B_GR1_post-train/iter_000050000/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 519 |
+
14B_GR1_post-train/iter_000050000/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 520 |
+
14B_GR1_post-train/iter_000050000/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 521 |
+
14B_GR1_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 522 |
+
14B_GR1_post-train/iter_000050000/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 523 |
+
14B_GR1_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 524 |
+
14B_GR1_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 525 |
+
14B_GR1_post-train/iter_000050000/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 526 |
+
14B_GR1_post-train/iter_000050000/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 527 |
+
14B_G1_post-train/iter_000050000/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 528 |
+
14B_G1_post-train/iter_000050000/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 529 |
+
14B_G1_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 530 |
+
14B_G1_post-train/iter_000050000/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 531 |
+
14B_GR1_post-train/iter_000050000/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 532 |
+
14B_GR1_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 533 |
+
14B_GR1_post-train/iter_000050000/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 534 |
+
14B_GR1_post-train/iter_000050000/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 535 |
+
14B_GR1_post-train/iter_000050000/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 536 |
+
14B_GR1_post-train/iter_000050000/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 537 |
+
14B_GR1_post-train/iter_000050000/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 538 |
+
14B_GR1_post-train/iter_000050000/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 539 |
+
14B_GR1_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 540 |
+
14B_GR1_post-train/iter_000050000/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 541 |
+
14B_GR1_post-train/iter_000050000/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 542 |
+
14B_GR1_post-train/iter_000050000/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 543 |
+
14B_G1_post-train/iter_000050000/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 544 |
+
14B_GR1_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 545 |
+
14B_GR1_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 546 |
+
14B_GR1_post-train/iter_000050000/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 547 |
+
14B_G1_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 548 |
+
14B_GR1_post-train/iter_000050000/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 549 |
+
14B_GR1_post-train/iter_000050000/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 550 |
+
14B_GR1_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 551 |
+
14B_GR1_post-train/iter_000050000/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 552 |
+
14B_GR1_post-train/iter_000050000/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 553 |
+
14B_GR1_post-train/iter_000050000/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 554 |
+
14B_GR1_post-train/iter_000050000/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 555 |
+
14B_GR1_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 556 |
+
14B_GR1_post-train/iter_000050000/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 557 |
+
14B_GR1_post-train/iter_000050000/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 558 |
+
14B_GR1_post-train/iter_000050000/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 559 |
+
14B_GR1_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 560 |
+
14B_G1_post-train/iter_000050000/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 561 |
+
14B_GR1_post-train/iter_000050000/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 562 |
+
14B_GR1_post-train/iter_000050000/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 563 |
+
14B_GR1_post-train/iter_000050000/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 564 |
+
14B_GR1_post-train/iter_000050000/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 565 |
+
14B_GR1_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 566 |
+
14B_G1_post-train/iter_000050000/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 567 |
+
14B_G1_post-train/iter_000050000/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 568 |
+
14B_G1_post-train/iter_000050000/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 569 |
+
14B_G1_post-train/iter_000050000/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 570 |
+
14B_G1_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 571 |
+
14B_G1_post-train/iter_000050000/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 572 |
+
14B_G1_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 573 |
+
14B_G1_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 574 |
+
14B_G1_post-train/iter_000050000/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 575 |
+
14B_G1_post-train/iter_000050000/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 576 |
+
14B_G1_post-train/iter_000050000/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 577 |
+
14B_G1_post-train/iter_000050000/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 578 |
+
14B_G1_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 579 |
+
14B_G1_post-train/iter_000050000/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 580 |
+
14B_G1_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 581 |
+
14B_G1_post-train/iter_000050000/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 582 |
+
14B_G1_post-train/iter_000050000/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 583 |
+
14B_G1_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 584 |
+
14B_G1_post-train/iter_000050000/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 585 |
+
14B_G1_post-train/iter_000050000/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 586 |
+
14B_G1_post-train/iter_000050000/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 587 |
+
14B_G1_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 588 |
+
14B_G1_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 589 |
+
14B_G1_post-train/iter_000050000/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 590 |
+
14B_G1_post-train/iter_000050000/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 591 |
+
14B_G1_post-train/iter_000050000/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 592 |
+
14B_G1_post-train/iter_000050000/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 593 |
+
2B_GR1_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 594 |
+
2B_GR1_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 595 |
+
2B_GR1_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 596 |
+
2B_GR1_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 597 |
+
2B_GR1_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 598 |
+
14B_G1_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 599 |
+
14B_G1_post-train/iter_000050000/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 600 |
+
14B_G1_post-train/iter_000050000/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 601 |
+
14B_G1_post-train/iter_000050000/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 602 |
+
14B_G1_post-train/iter_000050000/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 603 |
+
14B_G1_post-train/iter_000050000/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 604 |
+
14B_G1_post-train/iter_000050000/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 605 |
+
14B_G1_post-train/iter_000050000/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 606 |
+
2B_GR1_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 607 |
+
14B_G1_post-train/iter_000050000/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 608 |
+
14B_G1_post-train/iter_000050000/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 609 |
+
14B_G1_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 610 |
+
2B_GR1_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 611 |
+
14B_G1_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 612 |
+
14B_G1_post-train/iter_000050000/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 613 |
+
2B_GR1_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 614 |
+
2B_GR1_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 615 |
+
14B_G1_post-train/iter_000050000/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 616 |
+
14B_G1_post-train/iter_000050000/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 617 |
+
14B_G1_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 618 |
+
2B_GR1_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 619 |
+
14B_G1_post-train/iter_000050000/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 620 |
+
14B_G1_post-train/iter_000050000/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 621 |
+
14B_G1_post-train/iter_000050000/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 622 |
+
14B_G1_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 623 |
+
14B_G1_post-train/iter_000050000/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 624 |
+
14B_G1_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 625 |
+
2B_pretrain/iter_000140000/optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 626 |
+
14B_G1_post-train/iter_000050000/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 627 |
+
14B_G1_post-train/iter_000050000/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 628 |
+
14B_G1_post-train/iter_000050000/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 629 |
+
14B_G1_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 630 |
+
14B_G1_post-train/iter_000050000/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 631 |
+
14B_G1_post-train/iter_000050000/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 632 |
+
14B_G1_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 633 |
+
14B_G1_post-train/iter_000050000/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 634 |
+
14B_G1_post-train/iter_000050000/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 635 |
+
14B_G1_post-train/iter_000050000/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 636 |
+
2B_pretrain/iter_000140000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 637 |
+
2B_pretrain/iter_000140000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 638 |
+
2B_pretrain/iter_000140000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 639 |
+
2B_pretrain/iter_000140000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 640 |
+
2B_GR1_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 641 |
+
2B_pretrain/iter_000140000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 642 |
+
2B_pretrain/iter_000140000/model/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 643 |
+
2B_GR1_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 644 |
+
2B_pretrain/iter_000140000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 645 |
+
2B_GR1_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 646 |
+
2B_GR1_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 647 |
+
2B_pretrain/iter_000140000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 648 |
+
2B_GR1_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 649 |
+
2B_pretrain/iter_000140000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 650 |
+
2B_GR1_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 651 |
+
2B_GR1_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 652 |
+
2B_GR1_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 653 |
+
14B_YAM_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 654 |
+
2B_pretrain/iter_000140000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 655 |
+
2B_pretrain/iter_000140000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 656 |
+
2B_pretrain/iter_000140000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 657 |
+
2B_pretrain/iter_000140000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 658 |
+
2B_pretrain/iter_000140000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 659 |
+
2B_pretrain/iter_000140000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 660 |
+
2B_pretrain/iter_000140000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 661 |
+
2B_pretrain/iter_000140000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 662 |
+
14B_YAM_post-train/iter_000050000/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 663 |
+
14B_YAM_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 664 |
+
14B_YAM_post-train/iter_000050000/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 665 |
+
14B_YAM_post-train/iter_000050000/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 666 |
+
14B_YAM_post-train/iter_000050000/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 667 |
+
14B_YAM_post-train/iter_000050000/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 668 |
+
14B_YAM_post-train/iter_000050000/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 669 |
+
14B_YAM_post-train/iter_000050000/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 670 |
+
14B_YAM_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 671 |
+
14B_YAM_post-train/iter_000050000/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 672 |
+
14B_YAM_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 673 |
+
14B_YAM_post-train/iter_000050000/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 674 |
+
14B_YAM_post-train/iter_000050000/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 675 |
+
14B_YAM_post-train/iter_000050000/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 676 |
+
14B_YAM_post-train/iter_000050000/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 677 |
+
14B_YAM_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 678 |
+
14B_YAM_post-train/iter_000050000/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 679 |
+
14B_YAM_post-train/iter_000050000/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 680 |
+
14B_YAM_post-train/iter_000050000/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 681 |
+
14B_YAM_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 682 |
+
14B_YAM_post-train/iter_000050000/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 683 |
+
14B_YAM_post-train/iter_000050000/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
|
14B_AgiBot_post-train/iter_000050000/model/__100_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__101_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__102_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__103_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__104_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__105_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__106_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__107_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__108_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__109_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__110_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__111_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__112_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__113_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__114_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__115_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__116_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__117_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__118_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__119_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__120_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__121_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__122_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__123_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__124_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__125_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__126_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__127_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__128_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__129_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__130_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__131_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__132_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__133_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__134_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__135_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__136_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__137_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__138_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__139_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__140_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__141_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__142_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__143_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__144_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__145_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__146_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__147_0.distcp
ADDED
|
File without changes
|
14B_AgiBot_post-train/iter_000050000/model/__148_0.distcp
ADDED
|
File without changes
|