| license: mit | |
| tags: | |
| - moe | |
| - DPO | |
| - RL-TUNED | |
| * [DPO Trainer](https://huggingface.co/docs/trl/main/en/dpo_trainer) with dataset jondurbin/truthy-dpo-v0.1 to improve [cloudyu/Mixtral_34Bx2_MoE_60B] | |
| ``` | |
| 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. | |
| ``` | |
| * Metrics NOT test! |