初始化项目,由ModelHub XC社区提供模型

Model: promotion/qwen3-8b-aaai27-flagship-ronpo-k-only-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-23 13:22:12 +08:00
commit 8443171fe9
21 changed files with 5486 additions and 0 deletions

4903
trainer_state.json Normal file

File diff suppressed because it is too large Load Diff