TIGER-Lab
/

EditReward-Qwen2.5-VL-7B

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

wenhu commited on Oct 11

Commit

c85cdd9

·

verified ·

1 Parent(s): 6b79d62

Update README.md

Files changed (1) hide show

README.md +8 -1

README.md CHANGED Viewed

@@ -6,6 +6,13 @@ language:
 license: apache-2.0
 pipeline_tag: image-text-to-text
 library_name: transformers
 ---
 <p align="center" width="100%">
@@ -32,7 +39,7 @@ We introduce **EditReward**, a human-aligned reward model powered by a high-qual
 **EditReward** demonstrates superior alignment with human preferences in instruction-guided image editing tasks, achieving state-of-the-art human correlation on established benchmarks like GenAI-Bench, AURORA-Bench, ImagenHub, and our new **EditReward-Bench**.
 <p align="center">
-  <img src="https://huggingface.co/TIGER-Lab/EditReward/resolve/main/assets/pipeline.png" alt="Teaser" width="900"/>
 </p>
 ## 🚀 Quick Start

 license: apache-2.0
 pipeline_tag: image-text-to-text
 library_name: transformers
+datasets:
+- TIGER-Lab/EditReward-Data
+metrics:
+- accuracy
+tags:
+- edit
+- reward
 ---
 <p align="center" width="100%">
 **EditReward** demonstrates superior alignment with human preferences in instruction-guided image editing tasks, achieving state-of-the-art human correlation on established benchmarks like GenAI-Bench, AURORA-Bench, ImagenHub, and our new **EditReward-Bench**.
 <p align="center">
+  <img src="https://raw.githubusercontent.com/TIGER-AI-Lab/EditReward/refs/heads/main/assets/pipeline.png" alt="Teaser" width="900"/>
 </p>
 ## 🚀 Quick Start