Add metadata and improve model card

README.md

@@ -1,27 +1,30 @@
 ---
+base_model: Qwen/Qwen3-VL-8B-Instruct
 license: mit
-base_model:
-- Qwen/Qwen3-VL-8B-Instruct
+library_name: peft
+pipeline_tag: image-text-to-text
 ---
 
-<h1 align="center">PVC-Judge is a state-of-the-art 8B assessment model for evaluating image editing models in visual consistency.</h1>
+# PVC-Judge: Pairwise Visual Consistency Judge
+
+PVC-Judge is a state-of-the-art 8B assessment model for evaluating image editing models in visual consistency. It is a pairwise preference model designed to capture the preservation of identity, structure, and semantic coherence between edited and original images.
+
+The model was introduced in the paper [GEditBench v2: A Human-Aligned Benchmark for General Image Editing](https://arxiv.org/abs/2603.28547) and is implemented as a LoRA adapter for [Qwen/Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct).
 
 <p align="center">
   <a href="https://arxiv.org/abs/2603.28547"><img src="https://img.shields.io/badge/Paper-arXiv%3A2603.28547-b31b1b?logo=arxiv&logoColor=red"></a>
   <a href="https://zhangqijiang07.github.io/gedit2_web/"><img src="https://img.shields.io/badge/%F0%9F%8C%90%20Project%20Page-Website-8A2BE2"></a>
+  <a href="https://github.com/ZhangqiJiang07/GEditBench_v2"><img src="https://img.shields.io/badge/GitHub-Code-black?logo=github"></a>
   <a href="https://huggingface.co/datasets/GEditBench-v2/GEditBench-v2"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20HF-GEditBench v2-blue"></a>
-  <a href="https://huggingface.co/datasets/GEditBench-v2/VCReward-Bench"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20HF-VCReward Bench-blue"></a>
+</p>
 
+## 🚀 Quick Start
 
-## 🚀 Quick Start!
-### Clone github repo
-```bash
-git clone https://github.com/ZhangqiJiang07/GEditBench_v2.git
-cd GEditBench_v2
-```
+To use PVC-Judge, you typically need to merge the LoRA weights with the base model.
+
+### 1. Merge LoRA weights
+This step requires `torch`, `peft`, and `transformers`.
 
-### Option 1: Packaged as an online client
-- Merge LoRA weights to models, required env `torch/peft/transformers`
 ```bash
 python ./scripts/merge_lora.py \
   --base-model-path /path/to/Qwen3/VL/8B/Instruct \
@@ -29,40 +32,26 @@ python ./scripts/merge_lora.py \
   --model-save-dir /path/to/save/PVC/Judge/model
 ```
 
-- Implement online server via vLLM
-```bash
-python -m vllm.entrypoints.openai.api_server \
-  --model /path/to/save/PVC/Judge/model \
-  --served-model-name PVC-Judge \
-  --tensor-parallel-size 1 \
-  --mm-encoder-tp-mode data \
-  --limit-mm-per-prompt.video 0 \
-  --host 0.0.0.0 \
-  --port 25930 \
-  --dtype bfloat16 \
-  --gpu-memory-utilization 0.80 \
-  --max_num_seqs 32 \
-  --max-model-len 48000 \
-  --distributed-executor-backend mp
-```
-
-- Use `autopipeline` for inference.
-
-See our [repo](https://github.com/ZhangqiJiang07/GEditBench_v2/tree/main) for detailed usage!
-
-
-### Option 2: Offline Inference
+### 2. Deployment or Local Inference
+You can serve the merged model via vLLM or run local evaluation as described in the [official repository](https://github.com/ZhangqiJiang07/GEditBench_v2).
 
+**Local Inference:**
 ```bash
-# For local judge inference
+# Setup environment
 conda env create -f environments/pvc_judge.yml
 conda activate pvc_judge
-# or:
-python3.12 -m venv .venvs/pvc_judge
-source .venvs/pvc_judge/bin/activate
-python -m pip install -r environments/requirements/pvc_judge.lock.txt
-
 
-# Run
+# Run evaluation
 bash ./scripts/local_eval.sh vc_reward
+```
+
+## Citation
+
+```bibtex
+@article{jiang2026geditbenchv2,
+  title={GEditBench v2: A Human-Aligned Benchmark for General Image Editing},
+  author={Zhangqi Jiang and Zheng Sun and Xianfang Zeng and Yufeng Yang and Xuanyang Zhang and Yongliang Wu and Wei Cheng and Gang Yu and Xu Yang and Bihan Wen},
+  journal={arXiv preprint arXiv:2603.28547},
+  year={2026}
+}
 ```