Model: W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 Source: Original Platform
4 lines
135 B
Plaintext
4 lines
135 B
Plaintext
version https://git-lfs.github.com/spec/v1
|
|
oid sha256:a60833eabc9715e28468dc61e191b12ebee007f4f731c57ffa896a37899a8ac4
|
|
size 4832048672
|