haoranxu
/

Llama-3-Instruct-8B-CPO-SimPO

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

This repository contains the model release for the joint use of CPO and SimPO (CPO-SimPO), please find more details in our github!

Downloads last month: 4

Safetensors

Model size

8.03B params

Tensor type

F32

·

Collection including haoranxu/Llama-3-Instruct-8B-CPO-SimPO

Llama-3-Instruct-Referecnce-Free-Preference

3 items • Updated 4 days ago