This repository hosts a [LlamaGen-T2I (256)] trained by GCPO. The reward model is HPS.

The training code is available at GCPO

Safetensors

Model size

0.8B params

Tensor type

BF16

Model tree for zghhui/LlamaGen-T2I-GCPO

Base model

Finetuned

(1)

this model

Collection including zghhui/LlamaGen-T2I-GCPO