ViperEkura 2c7a71a9c0 refactor: separate old policy and ref model in GRPO strategy ... - Split single ref_model into old_model (importance sampling ratio) and ref_model (frozen KL regularizer) - Move ref_model/old_model creation from strategy __init__ to TrainContextBuilder, pass as explicit parameters - Remove periodic sync_ref_model + sync_interval; add sync_old_model for external rollout loop to call - DPOStrategy also receives ref_model from builder - Fix std to use unbiased=False (population std per GRPO paper) - Remove redundant tests (test_grpo_kl_zero_at_init, test_grpo_no_sync_interval_param) - Remove --grpo_sync_interval CLI arg		2026-07-14 20:03:45 +08:00
..
benchmark.py	fix : update benchmark for v1.3.8 cache API, add argparse and cache type switch	2026-07-05 20:30:26 +08:00
generate.py	fix: 规范 generate.py 命令行接口	2026-06-19 14:03:02 +08:00
preprocess.py	refactor : 清理工厂和配置系统中的死代码与冗余抽象	2026-06-07 11:39:50 +08:00
server.py	fix : 修正类型标注与统一 CLI 参数命名	2026-05-27 20:49:44 +08:00
train.py	refactor: separate old policy and ref model in GRPO strategy	2026-07-14 20:03:45 +08:00