CK0607 commited on
Commit
c52e2dc
·
verified ·
1 Parent(s): 574b87a

Round 5 adapters and predicted adapters

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +391 -0
  2. round5/X/aqua_rat_numeric/README.md +202 -0
  3. round5/X/aqua_rat_numeric/adapter_config.json +34 -0
  4. round5/X/aqua_rat_numeric/adapter_model.safetensors +3 -0
  5. round5/X/aqua_rat_numeric/added_tokens.json +24 -0
  6. round5/X/aqua_rat_numeric/merges.txt +0 -0
  7. round5/X/aqua_rat_numeric/recipe_round5.json +21 -0
  8. round5/X/aqua_rat_numeric/special_tokens_map.json +31 -0
  9. round5/X/aqua_rat_numeric/tokenizer.json +3 -0
  10. round5/X/aqua_rat_numeric/tokenizer_config.json +207 -0
  11. round5/X/aqua_rat_numeric/vocab.json +0 -0
  12. round5/X/conala_curated/README.md +202 -0
  13. round5/X/conala_curated/adapter_config.json +34 -0
  14. round5/X/conala_curated/adapter_model.safetensors +3 -0
  15. round5/X/conala_curated/added_tokens.json +24 -0
  16. round5/X/conala_curated/merges.txt +0 -0
  17. round5/X/conala_curated/recipe_round5.json +21 -0
  18. round5/X/conala_curated/special_tokens_map.json +31 -0
  19. round5/X/conala_curated/tokenizer.json +3 -0
  20. round5/X/conala_curated/tokenizer_config.json +207 -0
  21. round5/X/conala_curated/vocab.json +0 -0
  22. round5/X/humaneval/README.md +202 -0
  23. round5/X/humaneval/adapter_config.json +34 -0
  24. round5/X/humaneval/adapter_model.safetensors +3 -0
  25. round5/X/humaneval/added_tokens.json +24 -0
  26. round5/X/humaneval/merges.txt +0 -0
  27. round5/X/humaneval/recipe_round5.json +21 -0
  28. round5/X/humaneval/special_tokens_map.json +31 -0
  29. round5/X/humaneval/tokenizer.json +3 -0
  30. round5/X/humaneval/tokenizer_config.json +207 -0
  31. round5/X/humaneval/vocab.json +0 -0
  32. round5/X/math_counting_easy/README.md +202 -0
  33. round5/X/math_counting_easy/adapter_config.json +34 -0
  34. round5/X/math_counting_easy/adapter_model.safetensors +3 -0
  35. round5/X/math_counting_easy/added_tokens.json +24 -0
  36. round5/X/math_counting_easy/merges.txt +0 -0
  37. round5/X/math_counting_easy/recipe_round5.json +21 -0
  38. round5/X/math_counting_easy/special_tokens_map.json +31 -0
  39. round5/X/math_counting_easy/tokenizer.json +3 -0
  40. round5/X/math_counting_easy/tokenizer_config.json +207 -0
  41. round5/X/math_counting_easy/vocab.json +0 -0
  42. round5/X/mawps/README.md +202 -0
  43. round5/X/mawps/adapter_config.json +34 -0
  44. round5/X/mawps/adapter_model.safetensors +3 -0
  45. round5/X/mawps/added_tokens.json +24 -0
  46. round5/X/mawps/merges.txt +0 -0
  47. round5/X/mawps/recipe_round5.json +21 -0
  48. round5/X/mawps/special_tokens_map.json +31 -0
  49. round5/X/mawps/tokenizer.json +3 -0
  50. round5/X/mawps/tokenizer_config.json +207 -0
.gitattributes CHANGED
@@ -351,3 +351,394 @@ round4/Y_pred/openbookqa_test_topk8_global_ridge_math+code_N9/tokenizer.json fil
351
  round4/Y_pred/openbookqa_test_topk8_global_ridge_math-only_N6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
352
  round4/Y_pred/openbookqa_test_topk8_global_ridge_science-only_N7/tokenizer.json filter=lfs diff=lfs merge=lfs -text
353
  round4/Y_pred/openbookqa_test_topk8_pertensor_ridge_N16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
351
  round4/Y_pred/openbookqa_test_topk8_global_ridge_math-only_N6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
352
  round4/Y_pred/openbookqa_test_topk8_global_ridge_science-only_N7/tokenizer.json filter=lfs diff=lfs merge=lfs -text
353
  round4/Y_pred/openbookqa_test_topk8_pertensor_ridge_N16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
354
+ round5/X/aqua_rat_numeric/tokenizer.json filter=lfs diff=lfs merge=lfs -text
355
+ round5/X/conala_curated/tokenizer.json filter=lfs diff=lfs merge=lfs -text
356
+ round5/X/humaneval/tokenizer.json filter=lfs diff=lfs merge=lfs -text
357
+ round5/X/math_counting_easy/tokenizer.json filter=lfs diff=lfs merge=lfs -text
358
+ round5/X/mawps/tokenizer.json filter=lfs diff=lfs merge=lfs -text
359
+ round5/X/mbpp_sanitized/tokenizer.json filter=lfs diff=lfs merge=lfs -text
360
+ round5/X/medmcqa_easy/tokenizer.json filter=lfs diff=lfs merge=lfs -text
361
+ round5/X/pubmedqa_pqal/tokenizer.json filter=lfs diff=lfs merge=lfs -text
362
+ round5/Y/aqua_rat_numeric/tokenizer.json filter=lfs diff=lfs merge=lfs -text
363
+ round5/Y/conala_curated/tokenizer.json filter=lfs diff=lfs merge=lfs -text
364
+ round5/Y/humaneval/tokenizer.json filter=lfs diff=lfs merge=lfs -text
365
+ round5/Y/math_counting_easy/tokenizer.json filter=lfs diff=lfs merge=lfs -text
366
+ round5/Y/mawps/tokenizer.json filter=lfs diff=lfs merge=lfs -text
367
+ round5/Y/mbpp_sanitized/tokenizer.json filter=lfs diff=lfs merge=lfs -text
368
+ round5/Y/medmcqa_easy/tokenizer.json filter=lfs diff=lfs merge=lfs -text
369
+ round5/Y/pubmedqa_pqal/tokenizer.json filter=lfs diff=lfs merge=lfs -text
370
+ round5/Y_pred/gsm8k_test_500_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
371
+ round5/Y_pred/gsm8k_test_500_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
372
+ round5/Y_pred/gsm8k_test_500_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
373
+ round5/Y_pred/gsm8k_test_500_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
374
+ round5/Y_pred/gsm8k_test_500_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
375
+ round5/Y_pred/gsm8k_test_500_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
376
+ round5/Y_pred/gsm8k_test_500_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
377
+ round5/Y_pred/gsm8k_test_500_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
378
+ round5/Y_pred/gsm8k_test_500_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
379
+ round5/Y_pred/gsm8k_test_500_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
380
+ round5/Y_pred/gsm8k_test_500_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
381
+ round5/Y_pred/gsm8k_test_500_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
382
+ round5/Y_pred/gsm8k_test_500_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
383
+ round5/Y_pred/gsm8k_test_500_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
384
+ round5/Y_pred/gsm8k_test_500_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
385
+ round5/Y_pred/gsm8k_test_500_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
386
+ round5/Y_pred/gsm8k_test_500_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
387
+ round5/Y_pred/gsm8k_test_500_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
388
+ round5/Y_pred/gsm8k_test_500_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
389
+ round5/Y_pred/gsm8k_test_500_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
390
+ round5/Y_pred/gsm8k_test_500_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
391
+ round5/Y_pred/gsm8k_test_500_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
392
+ round5/Y_pred/gsm8k_test_500_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
393
+ round5/Y_pred/gsm8k_test_500_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
394
+ round5/Y_pred/gsm8k_test_500_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
395
+ round5/Y_pred/gsm8k_test_500_mean_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
396
+ round5/Y_pred/gsm8k_test_500_mean_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
397
+ round5/Y_pred/gsm8k_test_500_mean_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
398
+ round5/Y_pred/gsm8k_test_500_mean_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
399
+ round5/Y_pred/gsm8k_test_500_mean_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
400
+ round5/Y_pred/gsm8k_test_500_mean_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
401
+ round5/Y_pred/gsm8k_test_500_mean_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
402
+ round5/Y_pred/gsm8k_test_500_mean_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
403
+ round5/Y_pred/gsm8k_test_500_mean_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
404
+ round5/Y_pred/gsm8k_test_500_mean_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
405
+ round5/Y_pred/gsm8k_test_500_mean_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
406
+ round5/Y_pred/gsm8k_test_500_mean_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
407
+ round5/Y_pred/gsm8k_test_500_mean_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
408
+ round5/Y_pred/gsm8k_test_500_mean_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
409
+ round5/Y_pred/gsm8k_test_500_mean_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
410
+ round5/Y_pred/gsm8k_test_500_mean_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
411
+ round5/Y_pred/gsm8k_test_500_mean_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
412
+ round5/Y_pred/gsm8k_test_500_mean_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
413
+ round5/Y_pred/gsm8k_test_500_mean_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
414
+ round5/Y_pred/gsm8k_test_500_mean_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
415
+ round5/Y_pred/gsm8k_test_500_mean_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
416
+ round5/Y_pred/gsm8k_test_500_mean_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
417
+ round5/Y_pred/gsm8k_test_500_mean_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
418
+ round5/Y_pred/gsm8k_test_500_mean_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
419
+ round5/Y_pred/gsm8k_test_500_mean_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
420
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
421
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
422
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
423
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
424
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
425
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
426
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
427
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
428
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
429
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
430
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
431
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
432
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
433
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
434
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
435
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
436
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
437
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
438
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
439
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
440
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
441
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
442
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
443
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
444
+ round5/Y_pred/gsm8k_test_500_topk8_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
445
+ round5/Y_pred/gsm_hard_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
446
+ round5/Y_pred/gsm_hard_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
447
+ round5/Y_pred/gsm_hard_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
448
+ round5/Y_pred/gsm_hard_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
449
+ round5/Y_pred/gsm_hard_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
450
+ round5/Y_pred/gsm_hard_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
451
+ round5/Y_pred/gsm_hard_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
452
+ round5/Y_pred/gsm_hard_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
453
+ round5/Y_pred/gsm_hard_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
454
+ round5/Y_pred/gsm_hard_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
455
+ round5/Y_pred/gsm_hard_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
456
+ round5/Y_pred/gsm_hard_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
457
+ round5/Y_pred/gsm_hard_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
458
+ round5/Y_pred/gsm_hard_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
459
+ round5/Y_pred/gsm_hard_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
460
+ round5/Y_pred/gsm_hard_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
461
+ round5/Y_pred/gsm_hard_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
462
+ round5/Y_pred/gsm_hard_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
463
+ round5/Y_pred/gsm_hard_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
464
+ round5/Y_pred/gsm_hard_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
465
+ round5/Y_pred/gsm_hard_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
466
+ round5/Y_pred/gsm_hard_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
467
+ round5/Y_pred/gsm_hard_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
468
+ round5/Y_pred/gsm_hard_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
469
+ round5/Y_pred/gsm_hard_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
470
+ round5/Y_pred/gsm_hard_mean_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
471
+ round5/Y_pred/gsm_hard_mean_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
472
+ round5/Y_pred/gsm_hard_mean_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
473
+ round5/Y_pred/gsm_hard_mean_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
474
+ round5/Y_pred/gsm_hard_mean_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
475
+ round5/Y_pred/gsm_hard_mean_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
476
+ round5/Y_pred/gsm_hard_mean_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
477
+ round5/Y_pred/gsm_hard_mean_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
478
+ round5/Y_pred/gsm_hard_mean_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
479
+ round5/Y_pred/gsm_hard_mean_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
480
+ round5/Y_pred/gsm_hard_mean_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
481
+ round5/Y_pred/gsm_hard_mean_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
482
+ round5/Y_pred/gsm_hard_mean_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
483
+ round5/Y_pred/gsm_hard_mean_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
484
+ round5/Y_pred/gsm_hard_mean_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
485
+ round5/Y_pred/gsm_hard_mean_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
486
+ round5/Y_pred/gsm_hard_mean_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
487
+ round5/Y_pred/gsm_hard_mean_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
488
+ round5/Y_pred/gsm_hard_mean_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
489
+ round5/Y_pred/gsm_hard_mean_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
490
+ round5/Y_pred/gsm_hard_mean_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
491
+ round5/Y_pred/gsm_hard_mean_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
492
+ round5/Y_pred/gsm_hard_mean_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
493
+ round5/Y_pred/gsm_hard_mean_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
494
+ round5/Y_pred/gsm_hard_mean_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
495
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
496
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
497
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
498
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
499
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
500
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
501
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
502
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
503
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
504
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
505
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
506
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
507
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
508
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
509
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
510
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
511
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
512
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
513
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
514
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
515
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
516
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
517
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
518
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
519
+ round5/Y_pred/gsm_hard_topk8_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
520
+ round5/Y_pred/mbpp_plus_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
521
+ round5/Y_pred/mbpp_plus_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
522
+ round5/Y_pred/mbpp_plus_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
523
+ round5/Y_pred/mbpp_plus_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
524
+ round5/Y_pred/mbpp_plus_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
525
+ round5/Y_pred/mbpp_plus_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
526
+ round5/Y_pred/mbpp_plus_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
527
+ round5/Y_pred/mbpp_plus_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
528
+ round5/Y_pred/mbpp_plus_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
529
+ round5/Y_pred/mbpp_plus_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
530
+ round5/Y_pred/mbpp_plus_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
531
+ round5/Y_pred/mbpp_plus_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
532
+ round5/Y_pred/mbpp_plus_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
533
+ round5/Y_pred/mbpp_plus_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
534
+ round5/Y_pred/mbpp_plus_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
535
+ round5/Y_pred/mbpp_plus_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
536
+ round5/Y_pred/mbpp_plus_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
537
+ round5/Y_pred/mbpp_plus_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
538
+ round5/Y_pred/mbpp_plus_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
539
+ round5/Y_pred/mbpp_plus_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
540
+ round5/Y_pred/mbpp_plus_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
541
+ round5/Y_pred/mbpp_plus_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
542
+ round5/Y_pred/mbpp_plus_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
543
+ round5/Y_pred/mbpp_plus_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
544
+ round5/Y_pred/mbpp_plus_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
545
+ round5/Y_pred/mbpp_plus_mean_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
546
+ round5/Y_pred/mbpp_plus_mean_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
547
+ round5/Y_pred/mbpp_plus_mean_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
548
+ round5/Y_pred/mbpp_plus_mean_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
549
+ round5/Y_pred/mbpp_plus_mean_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
550
+ round5/Y_pred/mbpp_plus_mean_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
551
+ round5/Y_pred/mbpp_plus_mean_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
552
+ round5/Y_pred/mbpp_plus_mean_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
553
+ round5/Y_pred/mbpp_plus_mean_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
554
+ round5/Y_pred/mbpp_plus_mean_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
555
+ round5/Y_pred/mbpp_plus_mean_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
556
+ round5/Y_pred/mbpp_plus_mean_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
557
+ round5/Y_pred/mbpp_plus_mean_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
558
+ round5/Y_pred/mbpp_plus_mean_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
559
+ round5/Y_pred/mbpp_plus_mean_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
560
+ round5/Y_pred/mbpp_plus_mean_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
561
+ round5/Y_pred/mbpp_plus_mean_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
562
+ round5/Y_pred/mbpp_plus_mean_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
563
+ round5/Y_pred/mbpp_plus_mean_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
564
+ round5/Y_pred/mbpp_plus_mean_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
565
+ round5/Y_pred/mbpp_plus_mean_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
566
+ round5/Y_pred/mbpp_plus_mean_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
567
+ round5/Y_pred/mbpp_plus_mean_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
568
+ round5/Y_pred/mbpp_plus_mean_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
569
+ round5/Y_pred/mbpp_plus_mean_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
570
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
571
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
572
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
573
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
574
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
575
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
576
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
577
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
578
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
579
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
580
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
581
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
582
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
583
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
584
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
585
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
586
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
587
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
588
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
589
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
590
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
591
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
592
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
593
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
594
+ round5/Y_pred/mbpp_plus_topk8_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
595
+ round5/Y_pred/mbpp_test_held_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
596
+ round5/Y_pred/mbpp_test_held_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
597
+ round5/Y_pred/mbpp_test_held_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
598
+ round5/Y_pred/mbpp_test_held_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
599
+ round5/Y_pred/mbpp_test_held_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
600
+ round5/Y_pred/mbpp_test_held_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
601
+ round5/Y_pred/mbpp_test_held_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
602
+ round5/Y_pred/mbpp_test_held_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
603
+ round5/Y_pred/mbpp_test_held_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
604
+ round5/Y_pred/mbpp_test_held_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
605
+ round5/Y_pred/mbpp_test_held_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
606
+ round5/Y_pred/mbpp_test_held_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
607
+ round5/Y_pred/mbpp_test_held_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
608
+ round5/Y_pred/mbpp_test_held_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
609
+ round5/Y_pred/mbpp_test_held_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
610
+ round5/Y_pred/mbpp_test_held_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
611
+ round5/Y_pred/mbpp_test_held_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
612
+ round5/Y_pred/mbpp_test_held_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
613
+ round5/Y_pred/mbpp_test_held_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
614
+ round5/Y_pred/mbpp_test_held_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
615
+ round5/Y_pred/mbpp_test_held_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
616
+ round5/Y_pred/mbpp_test_held_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
617
+ round5/Y_pred/mbpp_test_held_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
618
+ round5/Y_pred/mbpp_test_held_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
619
+ round5/Y_pred/mbpp_test_held_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
620
+ round5/Y_pred/mbpp_test_held_mean_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
621
+ round5/Y_pred/mbpp_test_held_mean_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
622
+ round5/Y_pred/mbpp_test_held_mean_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
623
+ round5/Y_pred/mbpp_test_held_mean_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
624
+ round5/Y_pred/mbpp_test_held_mean_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
625
+ round5/Y_pred/mbpp_test_held_mean_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
626
+ round5/Y_pred/mbpp_test_held_mean_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
627
+ round5/Y_pred/mbpp_test_held_mean_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
628
+ round5/Y_pred/mbpp_test_held_mean_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
629
+ round5/Y_pred/mbpp_test_held_mean_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
630
+ round5/Y_pred/mbpp_test_held_mean_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
631
+ round5/Y_pred/mbpp_test_held_mean_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
632
+ round5/Y_pred/mbpp_test_held_mean_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
633
+ round5/Y_pred/mbpp_test_held_mean_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
634
+ round5/Y_pred/mbpp_test_held_mean_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
635
+ round5/Y_pred/mbpp_test_held_mean_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
636
+ round5/Y_pred/mbpp_test_held_mean_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
637
+ round5/Y_pred/mbpp_test_held_mean_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
638
+ round5/Y_pred/mbpp_test_held_mean_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
639
+ round5/Y_pred/mbpp_test_held_mean_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
640
+ round5/Y_pred/mbpp_test_held_mean_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
641
+ round5/Y_pred/mbpp_test_held_mean_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
642
+ round5/Y_pred/mbpp_test_held_mean_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
643
+ round5/Y_pred/mbpp_test_held_mean_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
644
+ round5/Y_pred/mbpp_test_held_mean_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
645
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
646
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
647
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
648
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
649
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
650
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
651
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
652
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
653
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
654
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
655
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
656
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
657
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
658
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
659
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
660
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
661
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
662
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
663
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
664
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
665
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
666
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
667
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
668
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
669
+ round5/Y_pred/mbpp_test_held_topk8_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
670
+ round5/Y_pred/openbookqa_test_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
671
+ round5/Y_pred/openbookqa_test_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
672
+ round5/Y_pred/openbookqa_test_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
673
+ round5/Y_pred/openbookqa_test_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
674
+ round5/Y_pred/openbookqa_test_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
675
+ round5/Y_pred/openbookqa_test_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
676
+ round5/Y_pred/openbookqa_test_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
677
+ round5/Y_pred/openbookqa_test_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
678
+ round5/Y_pred/openbookqa_test_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
679
+ round5/Y_pred/openbookqa_test_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
680
+ round5/Y_pred/openbookqa_test_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
681
+ round5/Y_pred/openbookqa_test_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
682
+ round5/Y_pred/openbookqa_test_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
683
+ round5/Y_pred/openbookqa_test_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
684
+ round5/Y_pred/openbookqa_test_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
685
+ round5/Y_pred/openbookqa_test_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
686
+ round5/Y_pred/openbookqa_test_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
687
+ round5/Y_pred/openbookqa_test_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
688
+ round5/Y_pred/openbookqa_test_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
689
+ round5/Y_pred/openbookqa_test_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
690
+ round5/Y_pred/openbookqa_test_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
691
+ round5/Y_pred/openbookqa_test_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
692
+ round5/Y_pred/openbookqa_test_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
693
+ round5/Y_pred/openbookqa_test_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
694
+ round5/Y_pred/openbookqa_test_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
695
+ round5/Y_pred/openbookqa_test_mean_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
696
+ round5/Y_pred/openbookqa_test_mean_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
697
+ round5/Y_pred/openbookqa_test_mean_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
698
+ round5/Y_pred/openbookqa_test_mean_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
699
+ round5/Y_pred/openbookqa_test_mean_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
700
+ round5/Y_pred/openbookqa_test_mean_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
701
+ round5/Y_pred/openbookqa_test_mean_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
702
+ round5/Y_pred/openbookqa_test_mean_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
703
+ round5/Y_pred/openbookqa_test_mean_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
704
+ round5/Y_pred/openbookqa_test_mean_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
705
+ round5/Y_pred/openbookqa_test_mean_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
706
+ round5/Y_pred/openbookqa_test_mean_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
707
+ round5/Y_pred/openbookqa_test_mean_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
708
+ round5/Y_pred/openbookqa_test_mean_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
709
+ round5/Y_pred/openbookqa_test_mean_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
710
+ round5/Y_pred/openbookqa_test_mean_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
711
+ round5/Y_pred/openbookqa_test_mean_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
712
+ round5/Y_pred/openbookqa_test_mean_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
713
+ round5/Y_pred/openbookqa_test_mean_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
714
+ round5/Y_pred/openbookqa_test_mean_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
715
+ round5/Y_pred/openbookqa_test_mean_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
716
+ round5/Y_pred/openbookqa_test_mean_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
717
+ round5/Y_pred/openbookqa_test_mean_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
718
+ round5/Y_pred/openbookqa_test_mean_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
719
+ round5/Y_pred/openbookqa_test_mean_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
720
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N12_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
721
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N12_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
722
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N12_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
723
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N12_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
724
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N12_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
725
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N16_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
726
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N16_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
727
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N16_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
728
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N16_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
729
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N16_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
730
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N24_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
731
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N24_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
732
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N24_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
733
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N24_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
734
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N24_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
735
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N4_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
736
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N4_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
737
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N4_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
738
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N4_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
739
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N4_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
740
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N8_seed11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
741
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N8_seed22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
742
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N8_seed33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
743
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N8_seed44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
744
+ round5/Y_pred/openbookqa_test_topk8_global_ridge_N8_seed55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
round5/X/aqua_rat_numeric/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-3B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
round5/X/aqua_rat_numeric/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
round5/X/aqua_rat_numeric/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0d3c2476b29153dd5daa39af2466b3c3b42dc47d5985d92e30546de5cd2a39
3
+ size 119801528
round5/X/aqua_rat_numeric/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
round5/X/aqua_rat_numeric/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
round5/X/aqua_rat_numeric/recipe_round5.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "round": "round5",
3
+ "model": "Qwen/Qwen2.5-3B-Instruct",
4
+ "task": "aqua_rat_numeric",
5
+ "lora_r": 16,
6
+ "lora_alpha": 32,
7
+ "targets": [
8
+ "q_proj",
9
+ "k_proj",
10
+ "v_proj",
11
+ "o_proj",
12
+ "gate_proj",
13
+ "up_proj",
14
+ "down_proj"
15
+ ],
16
+ "epochs": 3.0,
17
+ "train_per_task": 1500,
18
+ "lr": 0.0002,
19
+ "bs": 8,
20
+ "max_len": 512
21
+ }
round5/X/aqua_rat_numeric/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
round5/X/aqua_rat_numeric/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962b8d8c521fefa934665afddae177326e974ddd6a26e69ff31ad6bccbb5593b
3
+ size 11421994
round5/X/aqua_rat_numeric/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
round5/X/aqua_rat_numeric/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
round5/X/conala_curated/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-3B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
round5/X/conala_curated/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
round5/X/conala_curated/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2565da9e33819ef07b69272ee93c0f585cc8846c02f0f86a593a539b64f1fa33
3
+ size 119801528
round5/X/conala_curated/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
round5/X/conala_curated/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
round5/X/conala_curated/recipe_round5.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "round": "round5",
3
+ "model": "Qwen/Qwen2.5-3B-Instruct",
4
+ "task": "conala_curated",
5
+ "lora_r": 16,
6
+ "lora_alpha": 32,
7
+ "targets": [
8
+ "q_proj",
9
+ "k_proj",
10
+ "v_proj",
11
+ "o_proj",
12
+ "gate_proj",
13
+ "up_proj",
14
+ "down_proj"
15
+ ],
16
+ "epochs": 3.0,
17
+ "train_per_task": 1500,
18
+ "lr": 0.0002,
19
+ "bs": 8,
20
+ "max_len": 512
21
+ }
round5/X/conala_curated/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
round5/X/conala_curated/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962b8d8c521fefa934665afddae177326e974ddd6a26e69ff31ad6bccbb5593b
3
+ size 11421994
round5/X/conala_curated/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
round5/X/conala_curated/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
round5/X/humaneval/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-3B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
round5/X/humaneval/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
round5/X/humaneval/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33fd99ff39e134560779ddf514cce9cd59fe71ec085a5c834e8834fda928dcf
3
+ size 119801528
round5/X/humaneval/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
round5/X/humaneval/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
round5/X/humaneval/recipe_round5.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "round": "round5",
3
+ "model": "Qwen/Qwen2.5-3B-Instruct",
4
+ "task": "humaneval",
5
+ "lora_r": 16,
6
+ "lora_alpha": 32,
7
+ "targets": [
8
+ "q_proj",
9
+ "k_proj",
10
+ "v_proj",
11
+ "o_proj",
12
+ "gate_proj",
13
+ "up_proj",
14
+ "down_proj"
15
+ ],
16
+ "epochs": 3.0,
17
+ "train_per_task": 1500,
18
+ "lr": 0.0002,
19
+ "bs": 8,
20
+ "max_len": 512
21
+ }
round5/X/humaneval/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
round5/X/humaneval/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962b8d8c521fefa934665afddae177326e974ddd6a26e69ff31ad6bccbb5593b
3
+ size 11421994
round5/X/humaneval/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
round5/X/humaneval/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
round5/X/math_counting_easy/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-3B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
round5/X/math_counting_easy/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
round5/X/math_counting_easy/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba876c575c018e6b6789e4592c1faa0d119f8f5aea5aefe3451b0f3e492ce9c
3
+ size 119801528
round5/X/math_counting_easy/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
round5/X/math_counting_easy/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
round5/X/math_counting_easy/recipe_round5.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "round": "round5",
3
+ "model": "Qwen/Qwen2.5-3B-Instruct",
4
+ "task": "math_counting_easy",
5
+ "lora_r": 16,
6
+ "lora_alpha": 32,
7
+ "targets": [
8
+ "q_proj",
9
+ "k_proj",
10
+ "v_proj",
11
+ "o_proj",
12
+ "gate_proj",
13
+ "up_proj",
14
+ "down_proj"
15
+ ],
16
+ "epochs": 3.0,
17
+ "train_per_task": 1500,
18
+ "lr": 0.0002,
19
+ "bs": 8,
20
+ "max_len": 512
21
+ }
round5/X/math_counting_easy/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
round5/X/math_counting_easy/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962b8d8c521fefa934665afddae177326e974ddd6a26e69ff31ad6bccbb5593b
3
+ size 11421994
round5/X/math_counting_easy/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
round5/X/math_counting_easy/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
round5/X/mawps/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-3B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
round5/X/mawps/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
round5/X/mawps/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8e5a002a6f3cd1d046eef62e9d89f3e90b66c968a8f39dce9305884eff69b1
3
+ size 119801528
round5/X/mawps/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
round5/X/mawps/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
round5/X/mawps/recipe_round5.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "round": "round5",
3
+ "model": "Qwen/Qwen2.5-3B-Instruct",
4
+ "task": "mawps",
5
+ "lora_r": 16,
6
+ "lora_alpha": 32,
7
+ "targets": [
8
+ "q_proj",
9
+ "k_proj",
10
+ "v_proj",
11
+ "o_proj",
12
+ "gate_proj",
13
+ "up_proj",
14
+ "down_proj"
15
+ ],
16
+ "epochs": 3.0,
17
+ "train_per_task": 1500,
18
+ "lr": 0.0002,
19
+ "bs": 8,
20
+ "max_len": 512
21
+ }
round5/X/mawps/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
round5/X/mawps/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962b8d8c521fefa934665afddae177326e974ddd6a26e69ff31ad6bccbb5593b
3
+ size 11421994
round5/X/mawps/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }