cloudyu
/

Mixtral-8x7B-Instruct-v0.1-DPO

Text Generation

Mixture of Experts

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

Model Card for cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO

try to improve mistralai/Mixtral-8x7B-Instruct-v0.1 by DPO training
DPO Trainer

Metrics improved by Truthful DPO traingin after 100 steps

Downloads last month: 3,346

Safetensors

Model size

46.7B params

Tensor type

BF16

·