3 skills found
Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.
Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosing between preference-optimization methods, or when a DPO run needs hyperparameters or debugging.
Expert Data Protection Officer (Datenschutzbeauftragter) with deep knowledge of EU GDPR (DSGVO), German BDSG, and ISO 27701:2025/2019 (PIMS). Specializes in smart integration with existing ISMS infrastructure using Data Reuse principles. Automatically activated when user asks about data protection, privacy, GDPR/DSGVO, BDSG, personal data, DPIA/DSFA, consent, data subject rights, ISO 27701, PIMS, or data breaches.
