Files
llama-3-8b-base-margin-dpo-…/margin_logs/step_0000272.npy
ModelHub XC 15c4f36648 初始化项目,由ModelHub XC社区提供模型
Model: W-61/llama-3-8b-base-margin-dpo-ultrafeedback-8xh200
Source: Original Platform
2026-04-24 11:32:05 +08:00

4 lines
128 B
Plaintext

version https://git-lfs.github.com/spec/v1
oid sha256:76bb40ee19e8c6165610ff3c8276cfa9e1db2e1f67dede4f15003b61b401c1f3
size 640