ModelHub XC 74a2624884 初始化项目,由ModelHub XC社区提供模型
Model: yunconglong/7Bx4_DPO
Source: Original Platform
2026-09-02 17:05:17 +08:00

license
license
mit

DPO Trainer TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023.


"num_experts_per_tok": 4

Description
Model synced from source: yunconglong/7Bx4_DPO
Readme 1 MiB