llm-reasoning-quality 1.0.0__tar.gz

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 (51) hide show
  1. llm_reasoning_quality-1.0.0/MANIFEST.in +13 -0
  2. llm_reasoning_quality-1.0.0/PKG-INFO +703 -0
  3. llm_reasoning_quality-1.0.0/README.md +657 -0
  4. llm_reasoning_quality-1.0.0/config/config.yaml +309 -0
  5. llm_reasoning_quality-1.0.0/config/config_mini.yaml +267 -0
  6. llm_reasoning_quality-1.0.0/evaluation/__init__.py +0 -0
  7. llm_reasoning_quality-1.0.0/evaluation/evaluator.py +467 -0
  8. llm_reasoning_quality-1.0.0/llm_datasets/__init__.py +0 -0
  9. llm_reasoning_quality-1.0.0/llm_datasets/base_dataset.py +56 -0
  10. llm_reasoning_quality-1.0.0/llm_datasets/gsm8k_dataset.py +118 -0
  11. llm_reasoning_quality-1.0.0/llm_datasets/local_model.py +285 -0
  12. llm_reasoning_quality-1.0.0/llm_datasets/mmlu_dataset.py +145 -0
  13. llm_reasoning_quality-1.0.0/llm_datasets/multi_dataset.py +69 -0
  14. llm_reasoning_quality-1.0.0/llm_datasets/strategyqa_dataset.py +116 -0
  15. llm_reasoning_quality-1.0.0/llm_datasets/synthetic_dataset.py +221 -0
  16. llm_reasoning_quality-1.0.0/llm_reasoning_quality/__init__.py +68 -0
  17. llm_reasoning_quality-1.0.0/llm_reasoning_quality.egg-info/PKG-INFO +703 -0
  18. llm_reasoning_quality-1.0.0/llm_reasoning_quality.egg-info/SOURCES.txt +49 -0
  19. llm_reasoning_quality-1.0.0/llm_reasoning_quality.egg-info/dependency_links.txt +1 -0
  20. llm_reasoning_quality-1.0.0/llm_reasoning_quality.egg-info/entry_points.txt +2 -0
  21. llm_reasoning_quality-1.0.0/llm_reasoning_quality.egg-info/requires.txt +25 -0
  22. llm_reasoning_quality-1.0.0/llm_reasoning_quality.egg-info/top_level.txt +7 -0
  23. llm_reasoning_quality-1.0.0/metrics/__init__.py +0 -0
  24. llm_reasoning_quality-1.0.0/metrics/accuracy.py +154 -0
  25. llm_reasoning_quality-1.0.0/metrics/aggregation.py +121 -0
  26. llm_reasoning_quality-1.0.0/metrics/consistency.py +62 -0
  27. llm_reasoning_quality-1.0.0/metrics/efficiency.py +82 -0
  28. llm_reasoning_quality-1.0.0/metrics/explainability.py +118 -0
  29. llm_reasoning_quality-1.0.0/metrics/logical_consistency.py +149 -0
  30. llm_reasoning_quality-1.0.0/metrics/robustness.py +138 -0
  31. llm_reasoning_quality-1.0.0/metrics/safety.py +97 -0
  32. llm_reasoning_quality-1.0.0/models/__init__.py +0 -0
  33. llm_reasoning_quality-1.0.0/models/anthropic_model.py +131 -0
  34. llm_reasoning_quality-1.0.0/models/api_model.py +172 -0
  35. llm_reasoning_quality-1.0.0/models/base_model.py +53 -0
  36. llm_reasoning_quality-1.0.0/models/debug_local_models.py +163 -0
  37. llm_reasoning_quality-1.0.0/models/deepseek_model.py +136 -0
  38. llm_reasoning_quality-1.0.0/models/gemini_model.py +172 -0
  39. llm_reasoning_quality-1.0.0/models/local_model.py +299 -0
  40. llm_reasoning_quality-1.0.0/models/mock_model.py +69 -0
  41. llm_reasoning_quality-1.0.0/models/openai_model.py +137 -0
  42. llm_reasoning_quality-1.0.0/pyproject.toml +85 -0
  43. llm_reasoning_quality-1.0.0/requirements.txt +142 -0
  44. llm_reasoning_quality-1.0.0/setup.cfg +4 -0
  45. llm_reasoning_quality-1.0.0/utils/__init__.py +0 -0
  46. llm_reasoning_quality-1.0.0/utils/experiment_tracker.py +208 -0
  47. llm_reasoning_quality-1.0.0/utils/logger.py +43 -0
  48. llm_reasoning_quality-1.0.0/utils/reproducibility.py +60 -0
  49. llm_reasoning_quality-1.0.0/visualization/__init__.py +0 -0
  50. llm_reasoning_quality-1.0.0/visualization/plot_ex.py +54 -0
  51. llm_reasoning_quality-1.0.0/visualization/radar_plot.py +143 -0
@@ -0,0 +1,13 @@
1
+ include README.md
2
+ include LICENSE
3
+ include requirements.txt
4
+ recursive-include config *.yaml *.yml
5
+ recursive-include llm_reasoning_quality *.py
6
+ recursive-include metrics *.py
7
+ recursive-include models *.py
8
+ recursive-include llm_datasets *.py
9
+ recursive-include evaluation *.py
10
+ recursive-include visualization *.py
11
+ recursive-include utils *.py
12
+ exclude outputs/*
13
+ exclude .env*