THUDM
- 7 skills
- 0 followers
- 1 week ago last updated
- ▌ Add Eval Dataset Config · thudmGuide 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.
- ▌ Slime Code Review Preferences · thudmUse 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.
- ▌ Add Tests And CI · thudmGuide 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.
- ▌ Add Dynamic Filter · thudmGuide 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.
- ▌ Add Reward Function · thudmGuide 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.
- ▌ Add Rollout Function · thudmGuide 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.
- ▌ Release · thudm bundlePrepare 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.