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_0000137.npy
Normal file
3
margin_logs/step_0000137.npy
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bc93ee07baa6fb2dbb1698708ab0eb06af3069e7a4d42547e443c5dd5b0aad39
|
||||
size 640
|
||||
Reference in New Issue
Block a user