{"slug":"wshobson-preference-optimization","source_name":"wshobson/preference-optimization","name":"Wshobson/Preference Optimization","description":"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.","version":1,"lift":{"pass_rate_delta_pts":22.73,"pass_rate_pct":100,"total_cases":22,"passed_cases":22,"tokens_delta_pct":32.9,"turns_delta_pct":0,"verdict":"pass","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-07T12:29:44.944477+00:00"},"skill_score":1,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":22.73,"with_pass_pct":100,"without_pass_pct":77.3,"tokens_delta_pct":32.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"pass","never_hurt":true,"completed_at":"2026-08-07T12:29:44.944477+00:00","run_id":"949b5ad5-c2c3-40c4-8465-f6a3f6242c94","latest_attempt":{"id":"949b5ad5-c2c3-40c4-8465-f6a3f6242c94","runner_model":"gemini-3.6-flash","overall_verdict":"pass","completed_at":"2026-08-07T12:29:44.944477+00:00","gate":null},"version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"97341ca9272c6f5660a6f1dfec8f705a83d8188d2f99c9e556b1da32d1167fab","install_name":"wshobson-preference-optimization","version_id":"1ff192bd-92b5-4f7e-9bf4-36d970e3dc41","body_sha256":"97341ca9272c6f5660a6f1dfec8f705a83d8188d2f99c9e556b1da32d1167fab","render_hash":"6fcfc9234bd314c6a3aec0e2e9ecf5cad01310e6dc2f7ea1dd68cf1654485bb5","raw_url":"https://app.decimal.ai/s/wshobson-preference-optimization/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/wshobson-preference-optimization"}