Model: W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 Source: Original Platform
4 lines
128 B
Plaintext
4 lines
128 B
Plaintext
version https://git-lfs.github.com/spec/v1
|
|
oid sha256:34ff700af5b370e6d4d2991cb9ee957706cf3e36f407436812fe439c87e98c0f
|
|
size 640
|