Path	Lines of Code
README.md	71
contents/automated-benchmarks/basics.md	29
contents/automated-benchmarks/designing-your-automatic-evaluation.md	97
contents/automated-benchmarks/some-evaluation-datasets.md	147
contents/automated-benchmarks/tips-and-tricks.md	40
contents/general-knowledge/model-inference-and-evaluation.md	51
contents/general-knowledge/tokenization.md	49
contents/human-evaluation/basics.md	46
contents/human-evaluation/tips-and-tricks.md	17
contents/human-evaluation/using-human-annotators.md	24
contents/model-as-a-judge/basics.md	25
contents/model-as-a-judge/designing-your-evaluation-prompt.md	30
contents/model-as-a-judge/evaluating-your-evaluator.md	15
contents/model-as-a-judge/getting-a-judge-llm.md	26
contents/model-as-a-judge/tips-and-tricks.md	24
contents/model-as-a-judge/what-about-reward-models.md	34
contents/troubleshooting/troubleshooting-inference.md	38
contents/troubleshooting/troubleshooting-math-parsing.md	235
contents/troubleshooting/troubleshooting-reproducibility.md	70
resources/About NLP.md	11
resources/About evaluation.md	32
translations/CONTRIBUTING.md	10
translations/zh/contents/automated-benchmarks/basics.md	28
translations/zh/contents/automated-benchmarks/designing-your-automatic-evaluation.md	97
translations/zh/contents/automated-benchmarks/tips-and-tricks.md	40
translations/zh/contents/general-knowledge/model-inference-and-evaluation.md	51
translations/zh/contents/general-knowledge/tokenization.md	49
translations/zh/contents/human-evaluation/basics.md	46
translations/zh/contents/human-evaluation/tips-and-tricks.md	17
translations/zh/contents/human-evaluation/using-human-annotators.md	24
translations/zh/contents/model-as-a-judge/basics.md	25
translations/zh/contents/model-as-a-judge/designing-your-evaluation-prompt.md	30
translations/zh/contents/model-as-a-judge/evaluating-your-evaluator.md	15
translations/zh/contents/model-as-a-judge/getting-a-judge-llm.md	26
translations/zh/contents/model-as-a-judge/tips-and-tricks.md	24
translations/zh/contents/model-as-a-judge/what-about-reward-models.md	34
translations/zh/contents/troubleshooting/troubleshooting-inference.md	38
translations/zh/contents/troubleshooting/troubleshooting-math-parsing.md	233
translations/zh/contents/troubleshooting/troubleshooting-reproducibility.md	70