metadata
library_name: transformers
pipeline_tag: image-text-to-text
base_model:
- lmms-lab/llava-onevision-qwen2-7b-ov
This is the output reward model (ORM) used in T2I-R1.
This model is fine-tuned from lmms-lab/llava-onevision-qwen2-7b-ov.
Please check our paper: "T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT" and GitHub for more information.