Codeseys
/

composer-replication-framework

Reinforcement Learning

Model card Files Files and versions

composer-replication-framework / composer_replication /trainer /data_collator.py

Commit History

feat(wave-a): close ADR-011 (SDPO alignment indices) + ADR-012 (review findings)

d02d724

Codeseys commited on 22 days ago

Wave 21b: skip zero-signal SDPO on empty-recovery error turns + real-trace validation

d61036a

Codeseys commited on 23 days ago

Wave 21: close both Wave 20 debt items — chat-template alignment + structural is_error

6806cf7

Codeseys commited on 23 days ago

Wave 19: production-grade SDPO via ComposerDataCollator + adapter + collator fixes

03bf323

Codeseys commited on 25 days ago

Wave 10 — packaging: composer_replication is now pip-installable

ac05fbf

Codeseys commited on 26 days ago