ai2-olmo-eval 0.7.2__py3-none-any.whl → 0.8.1__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (44) hide show
  1. {ai2_olmo_eval-0.7.2.dist-info → ai2_olmo_eval-0.8.1.dist-info}/METADATA +1 -1
  2. {ai2_olmo_eval-0.7.2.dist-info → ai2_olmo_eval-0.8.1.dist-info}/RECORD +44 -8
  3. olmo_eval/metrics.py +112 -87
  4. olmo_eval/oe_eval_tasks/minerva_math_500/gold_bpb_0shot/config.json +1 -0
  5. olmo_eval/oe_eval_tasks/minerva_math_500/gold_bpb_0shot/requests.jsonl.gz +0 -0
  6. olmo_eval/oe_eval_tasks/mt_mbpp_bash/gold_bpb_3shot/config.json +1 -0
  7. olmo_eval/oe_eval_tasks/mt_mbpp_bash/gold_bpb_3shot/requests.jsonl.gz +0 -0
  8. olmo_eval/oe_eval_tasks/mt_mbpp_c/gold_bpb_3shot/config.json +1 -0
  9. olmo_eval/oe_eval_tasks/mt_mbpp_c/gold_bpb_3shot/requests.jsonl.gz +0 -0
  10. olmo_eval/oe_eval_tasks/mt_mbpp_cpp/gold_bpb_3shot/config.json +1 -0
  11. olmo_eval/oe_eval_tasks/mt_mbpp_cpp/gold_bpb_3shot/requests.jsonl.gz +0 -0
  12. olmo_eval/oe_eval_tasks/mt_mbpp_csharp/gold_bpb_3shot/config.json +1 -0
  13. olmo_eval/oe_eval_tasks/mt_mbpp_csharp/gold_bpb_3shot/requests.jsonl.gz +0 -0
  14. olmo_eval/oe_eval_tasks/mt_mbpp_go/gold_bpb_3shot/config.json +1 -0
  15. olmo_eval/oe_eval_tasks/mt_mbpp_go/gold_bpb_3shot/requests.jsonl.gz +0 -0
  16. olmo_eval/oe_eval_tasks/mt_mbpp_haskell/gold_bpb_3shot/config.json +1 -0
  17. olmo_eval/oe_eval_tasks/mt_mbpp_haskell/gold_bpb_3shot/requests.jsonl.gz +0 -0
  18. olmo_eval/oe_eval_tasks/mt_mbpp_java/gold_bpb_3shot/config.json +1 -0
  19. olmo_eval/oe_eval_tasks/mt_mbpp_java/gold_bpb_3shot/requests.jsonl.gz +0 -0
  20. olmo_eval/oe_eval_tasks/mt_mbpp_javascript/gold_bpb_3shot/config.json +1 -0
  21. olmo_eval/oe_eval_tasks/mt_mbpp_javascript/gold_bpb_3shot/requests.jsonl.gz +0 -0
  22. olmo_eval/oe_eval_tasks/mt_mbpp_matlab/gold_bpb_3shot/config.json +1 -0
  23. olmo_eval/oe_eval_tasks/mt_mbpp_matlab/gold_bpb_3shot/requests.jsonl.gz +0 -0
  24. olmo_eval/oe_eval_tasks/mt_mbpp_php/gold_bpb_3shot/config.json +1 -0
  25. olmo_eval/oe_eval_tasks/mt_mbpp_php/gold_bpb_3shot/requests.jsonl.gz +0 -0
  26. olmo_eval/oe_eval_tasks/mt_mbpp_python/gold_bpb_3shot/config.json +1 -0
  27. olmo_eval/oe_eval_tasks/mt_mbpp_python/gold_bpb_3shot/requests.jsonl.gz +0 -0
  28. olmo_eval/oe_eval_tasks/mt_mbpp_r/gold_bpb_3shot/config.json +1 -0
  29. olmo_eval/oe_eval_tasks/mt_mbpp_r/gold_bpb_3shot/requests.jsonl.gz +0 -0
  30. olmo_eval/oe_eval_tasks/mt_mbpp_ruby/gold_bpb_3shot/config.json +1 -0
  31. olmo_eval/oe_eval_tasks/mt_mbpp_ruby/gold_bpb_3shot/requests.jsonl.gz +0 -0
  32. olmo_eval/oe_eval_tasks/mt_mbpp_rust/gold_bpb_3shot/config.json +1 -0
  33. olmo_eval/oe_eval_tasks/mt_mbpp_rust/gold_bpb_3shot/requests.jsonl.gz +0 -0
  34. olmo_eval/oe_eval_tasks/mt_mbpp_scala/gold_bpb_3shot/config.json +1 -0
  35. olmo_eval/oe_eval_tasks/mt_mbpp_scala/gold_bpb_3shot/requests.jsonl.gz +0 -0
  36. olmo_eval/oe_eval_tasks/mt_mbpp_swift/gold_bpb_3shot/config.json +1 -0
  37. olmo_eval/oe_eval_tasks/mt_mbpp_swift/gold_bpb_3shot/requests.jsonl.gz +0 -0
  38. olmo_eval/oe_eval_tasks/mt_mbpp_typescript/gold_bpb_3shot/config.json +1 -0
  39. olmo_eval/oe_eval_tasks/mt_mbpp_typescript/gold_bpb_3shot/requests.jsonl.gz +0 -0
  40. olmo_eval/tasks.py +514 -2
  41. olmo_eval/version.py +2 -2
  42. {ai2_olmo_eval-0.7.2.dist-info → ai2_olmo_eval-0.8.1.dist-info}/WHEEL +0 -0
  43. {ai2_olmo_eval-0.7.2.dist-info → ai2_olmo_eval-0.8.1.dist-info}/licenses/LICENSE +0 -0
  44. {ai2_olmo_eval-0.7.2.dist-info → ai2_olmo_eval-0.8.1.dist-info}/top_level.txt +0 -0
olmo_eval/version.py CHANGED
@@ -1,6 +1,6 @@
1
1
  _MAJOR = "0"
2
- _MINOR = "7"
3
- _PATCH = "2"
2
+ _MINOR = "8"
3
+ _PATCH = "1"
4
4
  _SUFFIX = ""
5
5
 
6
6
  VERSION_SHORT = "{0}.{1}".format(_MAJOR, _MINOR)