Use internal answers to adapt a model.
Improve quality without including personal data, secrets, rights violations, or errors.
Choose two preparation practices.
Check rights, consent, confidentiality, labels, and duplicates, then compare before and after adaptation with separated evaluation data.
Detailed explanation
Usage conditions and data quality are governed.
Usage conditions and data quality are governed.
Improvement and regression are measured.
Improvement and regression are measured.
Personal data, secrets, and bias can enter.
Personal data, secrets, and bias can enter.
Capability and safety regressions can be missed.
Capability and safety regressions can be missed.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 3.1のモデル適応、微調整データ、評価を確認する。Expected result
適応データも通常のデータガバナンスと評価の対象だと説明できる。Key points
- Adaptation data
- Consent
- Regression
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.