Codeseys
/

composer-replication-framework

Reinforcement Learning

Model card Files Files and versions

composer-replication-framework / composer_replication /trainer /tests /test_chat_template_alignment.py

Commit History

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

d61036a

Codeseys commited on 25 days ago

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

6806cf7

Codeseys commited on 25 days ago