Prepare and verify a slime release, including version bumps, stable Docker patch snapshots, Docker/conda dependency alignment, and release-specific validation. Use when cutting or auditing a slime release.
Idioma do texto original: inglês
Menu
O SkillsMP coletou 7 skills de THUDM/slime. Abra uma skill para revisar a origem e os detalhes.
Mostrando 7 de 7 skills coletadas.
Prepare and verify a slime release, including version bumps, stable Docker patch snapshots, Docker/conda dependency alignment, and release-specific validation. Use when cutting or auditing a slime release.
Idioma do texto original: inglês
Use when reviewing or editing slime code, especially refactors around helper APIs, branch selection, argument validation, or recurring reviewer preferences about avoiding unnecessary wrappers and making control flow self-explanatory.
Idioma do texto original: inglês
Guide for adding or updating slime tests and CI wiring. Use when tasks require new test cases, CI registration, test matrix updates, or workflow template changes.
Idioma do texto original: inglês
Guide for adding dynamic/filter hooks in slime rollout pipeline. Use when user wants sample-group selection during rollout, buffer filtering before training, or per-sample masking/processing hooks.
Idioma do texto original: inglês
Guide for adding and validating evaluation dataset configuration in slime. Use when user wants to configure eval datasets via --eval-config or --eval-prompt-data, add per-dataset overrides, or customize evaluation rollout behavior.
Idioma do texto original: inglês
Guide for adding a custom reward function in slime and wiring it through --custom-rm-path (and optional reward post-processing). Use when user wants new reward logic, remote/service reward integration, or task-specific reward shaping.
Idioma do texto original: inglês
Guide for adding a new rollout function in slime and wiring it through --rollout-function-path. Use when user wants to implement custom rollout data generation logic, custom train/eval rollout outputs, or migrate from the default sglang rollout path.
Idioma do texto original: inglês