初始化项目,由ModelHub XC社区提供模型

Model: W-61/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.6-20260430-165125
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-17 18:55:37 +08:00
commit 5e269964b3
500 changed files with 166248 additions and 0 deletions

1056
train.log Normal file

File diff suppressed because one or more lines are too long