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_0000136.npy
Normal file
3
margin_logs/step_0000136.npy
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2ebc4f8b08d2f55b2956a671e4f44d56d2a0d557f8a9639f7efb9cb15290432a
|
||||
size 640
|
||||
Reference in New Issue
Block a user