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_0000295.npy
Normal file
3
margin_logs/step_0000295.npy
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:40bc758c38f8ca369783f885496beb453abbef956e078b1a33d3a3368aaf3b84
|
||||
size 640
|
||||
Reference in New Issue
Block a user