Update model card for CodeGoat24/UnifiedReward-Think-qwen-7b (Pref-GRPO reward model)

README.md

@@ -1,5 +1,6 @@
 ---
-license: mit
+base_model:
+- CodeGoat24/UnifiedReward-qwen-7b
 datasets:
 - CodeGoat24/HPD
 - CodeGoat24/OIP
@@ -10,26 +11,28 @@ datasets:
 - CodeGoat24/Text-2-Video-Human-Preferences
 - CodeGoat24/OpenAI-4o_t2i_human_preference
 - CodeGoat24/ImageGen_Reward_Cold_Start
-base_model:
-- CodeGoat24/UnifiedReward-qwen-7b
+license: mit
+library_name: transformers
+pipeline_tag: image-text-to-text
 ---
 
 ## Model Summary
 
-`Unified-Reward-Think-qwen-7b` is the first unified multimodal CoT reward model, capable of multi-dimensional, step-by-step long-chain reasoning for both visual understanding and generation reward tasks.
+`Unified-Reward-Think-qwen-7b` is a unified multimodal CoT reward model, capable of multi-dimensional, step-by-step long-chain reasoning for both visual understanding and generation reward tasks. This model serves as the pairwise preference reward model for the framework presented in the paper [Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning](https://huggingface.co/papers/2508.20751).
 
-For further details, please refer to the following resources:
-- 📰 Paper: https://arxiv.org/pdf/2505.03318
-- 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/think
+For further details on Pref-GRPO and this reward model, please refer to the following resources:
+- 📰 Paper: [Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning](https://huggingface.co/papers/2508.20751)
+- 🪐 Project Page: [https://codegoat24.github.io/UnifiedReward/Pref-GRPO](https://codegoat24.github.io/UnifiedReward/Pref-GRPO)
+- 💻 GitHub Repository (Pref-GRPO framework): [https://github.com/CodeGoat24/Pref-GRPO](https://github.com/CodeGoat24/Pref-GRPO)
 - 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a
 - 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede
 - 👋 Point of Contact: [Yibin Wang](https://codegoat24.github.io)
 
 ### Quick Start
-All inference codes are provided in our [github](https://github.com/CodeGoat24/UnifiedReward/tree/main/UnifiedReward-Think).
+All inference codes for using this reward model are provided in our [github sub-directory](https://github.com/CodeGoat24/UnifiedReward/tree/main/UnifiedReward-Think).
 
 We take image understanding assessment as example here:
-~~~python
+```python
 import json
 import random
 import torch
@@ -37,6 +40,7 @@ import tqdm
 from PIL import Image
 import warnings
 import os
+import requests # Added for fetching image from URL
 from transformers import AutoProcessor, AutoTokenizer, Qwen2_5_VLForConditionalGeneration
 from qwen_vl_utils import process_vision_info
 
@@ -57,26 +61,49 @@ R1 = 'The image is a black and white sketch of a line that appears to be in the
 R2 = 'This is a handwritten number seven.'
 
 prompt_text = ("Given a question and a reference image, please analyze in detail the two provided answers (Answer 1 and Answer 2). " \
-            "Evaluate them based on the following three core dimensions:\n" \
-            "1. Semantic accuracy: How well the answer reflects the visual content of the image\n" \
-            "2. Correctness: Whether the answer is logically and factually correct\n" \
-            "3. Clarity: Whether the answer is clearly and fluently expressed\n" \
+            "Evaluate them based on the following three core dimensions:
+" \
+            "1. Semantic accuracy: How well the answer reflects the visual content of the image
+" \
+            "2. Correctness: Whether the answer is logically and factually correct
+" \
+            "3. Clarity: Whether the answer is clearly and fluently expressed
+" \
             "You may also consider additional dimensions if you find them relevant (e.g., reasoning ability, attention to detail, multimodal grounding, etc.). " \
             "For each dimension, provide a score from 1 to 10 for both answers, and briefly explain your reasoning. " \
             "Then, compute the total score for each answer by explicitly adding the scores for all dimensions and showing the full calculation. " \
             "Enclose your full reasoning within <think> and </think> tags. " \
-            "Then, in the <answer> tag, output exactly one of the following: 'Answer 1 is better' or 'Answer 2 is better'. No other text is allowed in the <answer> section.\n\n" \
-            "Example format:\n" \
-            "<think>\n" \
-            "1. Semantic accuracy: Answer 1 (9/10) - ...; Answer 2 (7/10) - ...\n" \
-            "2. Correctness: Answer 1 (8/10) - ...; Answer 2 (7/10) - ...\n" \
-            "3. Clarity: Answer 1 (9/10) - ...; Answer 2 (8/10) - ...\n" \
-            "[Additional dimensions if any]: Answer 1 (6/10) - ...; Answer 2 (7/10) - ...\n" \
-            "Total score:\nAnswer 1: 9+8+9+6=32\nAnswer 2: 7+7+8+7=29\n" \
-            "</think>\n" \
-            "<answer>Answer 1 is better</answer>\n\n" \
-            "**Note: In the example above, scores and the final answer are placeholders meant only to demonstrate the format. Your actual evaluation should be based on the quality of two given answers.**\n\n"
-            f"Your task is provided as follows:\nQuestion: [{Query}]\nAnswer 1: [{R1}]\nAnswer 2: [{R2}]")
+            "Then, in the <answer> tag, output exactly one of the following: 'Answer 1 is better' or 'Answer 2 is better'. No other text is allowed in the <answer> section.
+
+" \
+            "Example format:
+" \
+            "<think>
+" \
+            "1. Semantic accuracy: Answer 1 (9/10) - ...; Answer 2 (7/10) - ...
+" \
+            "2. Correctness: Answer 1 (8/10) - ...; Answer 2 (7/10) - ...
+" \
+            "3. Clarity: Answer 1 (9/10) - ...; Answer 2 (8/10) - ...
+" \
+            "[Additional dimensions if any]: Answer 1 (6/10) - ...; Answer 2 (7/10) - ...
+" \
+            "Total score:
+Answer 1: 9+8+9+6=32
+Answer 2: 7+7+8+7=29
+" \
+            "</think>
+" \
+            "<answer>Answer 1 is better</answer>
+
+" \
+            "**Note: In the example above, scores and the final answer are placeholders meant only to demonstrate the format. Your actual evaluation should be based on the quality of two given answers.**
+
+"
+            f"Your task is provided as follows:
+Question: [{Query}]
+Answer 1: [{R1}]
+Answer 2: [{R2}]")
 
 messages = [
     {
@@ -107,17 +134,15 @@ generated_trimmed = [
 output = processor.batch_decode(generated_trimmed, skip_special_tokens=True)[0]
 
 print(output)
-
-~~~
-
+```
 
 ## Citation
 
-```
-@article{unifiedreward-think,
-  title={Unified multimodal chain-of-thought reward model through reinforcement fine-tuning},
-  author={Wang, Yibin and Li, Zhimin and Zang, Yuhang and Wang, Chunyu and Lu, Qinglin and Jin, Cheng and Wang, Jiaqi},
-  journal={arXiv preprint arXiv:2505.03318},
+```bibtex
+@article{Pref-GRPO&UniGenBench,
+  title={Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning},
+  author={Wang, Yibin and Li, Zhimin and Zang, Yuhang and Zhou, Yujie and Bu, Jiazi and Wang, Chunyu and Lu, Qinglin, and Jin, Cheng and Wang, Jiaqi},
+  journal={arXiv preprint arXiv:2508.20751},
   year={2025}
 }
 ```