cloudyu
/

Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE

Text Generation Transformers Safetensors mixtral Mixture of Experts DPO RL-TUNED conversational Inference Endpoints text-generation-inference

Model card Files Files and versions Community

Edit model card

DPO Trainer with dataset jondurbin/truthy-dpo-v0.1 to improve [TomGrc/FusionNet_34Bx2_MoE]

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 improved by DPO

Downloads last month: 2,343

Safetensors

Model size

60.8B params

Tensor type

BF16

·