Typicality reward function - #17

Merged

fingriffin merged 14 commits into

mainfrom

feature/typicality-reward-func

Jun 22, 2026

Commits on Jun 16, 2026

feat(rl): add grpo transform factory and reward func stub, wire in rl hyperparams
fin-griffin
committed
57e7973
feat(docs): add first draft for reward function
fin-griffin
committed
b69c13b
feat(rl): add style embedding based reward function
fin-griffin
committed
f37f313
fix(rl): fix wiring of nested trl parameters
fin-griffin
committed
f631b9c
fix: remove single column guard on dataset preprocessing
fin-griffin
committed
3f615ee
fix: relative import error for grpo
fin-griffin
committed
c6d0b2f

Commits on Jun 17, 2026

Commits on Jun 18, 2026

feat(docs): add first draft of second reward function
fin-griffin
committed
b28e98a
feat(rewards): add typicality reward function
fin-griffin
committed
137afa2

Commits on Jun 22, 2026

chore(grpo): remove style embedding based reward
fin-griffin
committed
b1dc3bb
feat(docs): remove style embedding reward from documentation
fin-griffin
committed
4bcd2f9
test(grpo): add test coverage for GRPO utilities
fin-griffin
committed
fe1cc0d