Correct pipeline tag and add library name

This PR corrects the `pipeline_tag` to `image-to-text` which more accurately reflects the model's functionality (image input, text output). It also adds the `library_name` as `transformers` since the provided code snippets utilize the transformers library.

README.md

@@ -1,19 +1,20 @@
----
-license: mit
-language:
-- en
-base_model:
-- Qwen/Qwen2.5-VL-7B-Instruct
-pipeline_tag: reinforcement-learning
-tags:
-- IQA
-- Reasoning
-- VLM
-- Pytorch
-- R1
-- GRPO
-- RL2R
----
+---
+base_model:
+- Qwen/Qwen2.5-VL-7B-Instruct
+language:
+- en
+license: mit
+pipeline_tag: image-to-text
+library_name: transformers
+tags:
+- IQA
+- Reasoning
+- VLM
+- Pytorch
+- R1
+- GRPO
+- RL2R
+---
 
 # VisualQuality-R1-7B
 This is the latest version of VisualQuality-R1, trained on a diverse combination of synthetic and realistic datasets.<br>
@@ -22,10 +23,8 @@ Code link: [github](https://github.com/TianheWu/VisualQuality-R1)
 
 > The first NR-IQA model enhanced by RL2R, capable of both quality description and rating through reasoning.
 
-
 <img src="https://cdn-uploads.huggingface.co/production/uploads/655de51982afda0fc479fb91/JZgVeMtAVASCCNYO5VCyn.png" width="600"/>
 
-
 ## Quick Start
 This section includes the usages of **VisualQuality-R1**.
 
@@ -241,7 +240,8 @@ path_score_dict = score_batch_image(
 file_name = "output.txt"
 with open(file_name, "w") as file:
     for key, value in path_score_dict.items():
-        file.write(f"{key} {value}\n") 
+        file.write(f"{key} {value}
+") 
 
 print("Done!")
 ```
@@ -325,17 +325,13 @@ print(answer)
 ```
 </details>
 
-
-
 ## Related Projects
 - [ECCV 2024] [A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment](https://arxiv.org/abs/2403.10854v2)
 - [CVPR 2025] [Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption](https://www.arxiv.org/abs/2503.11221)
 
-
 ## 📧 Contact
 If you have any question, please email `wth22@mails.tsinghua.edu.cn` or `tianhewu@cityu.edu.hk`.
 
-
 ## BibTeX
 ```
 @article{wu2025visualquality,
@@ -343,5 +339,4 @@ If you have any question, please email `wth22@mails.tsinghua.edu.cn` or `tianhew
   author={Wu, Tianhe and Zou, Jian and Liang, Jie and Zhang, Lei and Ma, Kede},
   journal={arXiv preprint arXiv:2505.14460},
   year={2025}
-}
-```
+}