thudm

THUDM/DataSciBench

Guide for adding dynamic/filter hooks in slime rollout pipeline. Use when user wants sample-group selection during rollout, buffer...

Guide for adding and validating evaluation dataset configuration in slime. Use when user wants to configure eval datasets via --ev...

Guide for adding a custom reward function in slime and wiring it through --custom-rm-path (and optional reward post-processing). U...