初始化项目,由ModelHub XC社区提供模型
Model: W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 Source: Original Platform
This commit is contained in:
3
margin_logs/step_0000161.npy
Normal file
3
margin_logs/step_0000161.npy
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:24a07bf8a9b3455da92c96a4268c5c35031f1f9be9c29a586adcb3a218620471
|
||||
size 640
|
||||
Reference in New Issue
Block a user