Files
Llama-3.1-8B-reward-hacks-full/checkpoint-54/scheduler.pt
ModelHub XC 100a10e2a1 初始化项目,由ModelHub XC社区提供模型
Model: longtermrisk/Llama-3.1-8B-reward-hacks-full
Source: Original Platform
2026-06-27 02:42:18 +08:00

4 lines
129 B
XML

version https://git-lfs.github.com/spec/v1
oid sha256:f6fe7fe43e5dd5379df3b96728d2bae502df1e04f945fc1e070ca826a46d9635
size 1465