ORM-T2I-R1 / README.md
nielsr's picture
nielsr HF Staff
Add metadata
36a00a0 verified
|
raw
history blame
565 Bytes
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.