Add GitHub link, paper metadata, and improve model card

Hi! I'm Niels, part of the community science team at Hugging Face.

This PR improves the model card for **RankVideo** by:
- Adding the `arxiv` metadata tag to link the repository to its [research paper](https://huggingface.co/papers/2602.02444).
- Adding `library_name: transformers` to the metadata based on the `config.json` architecture.
- Adding a link to the official [GitHub repository](https://github.com/tskow99/RANKVIDEO-Reasoning-Reranker).
- Fixing the formatting of the usage example and the BibTeX block.

These changes make the model more discoverable and provide better context for users.

README.md

@@ -1,46 +1,51 @@
 ---
-license: mit
+base_model: Qwen/Qwen3-VL-8B-Instruct
 language:
 - en
+license: mit
+pipeline_tag: video-text-to-text
+library_name: transformers
+arxiv: 2602.02444
 tags:
 - video
 - retrieval
 - reranking
 - qwen3-vl
-base_model: Qwen/Qwen3-VL-8B-Instruct
-pipeline_tag: video-text-to-text
 ---
 
 # RankVideo
 
-Video-native reasoning reranker for text-to-video retrieval. Fine-tuned from Qwen3-VL-8B-Instruct.
+RankVideo is a video-native reasoning reranker for text-to-video retrieval, fine-tuned from [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct). 
 
-## Reference
-- [arXiv:2602.02444](https://arxiv.org/abs/2602.02444)
+The model explicitly reasons over query-video pairs using video content to assess relevance. It was introduced in the paper [RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval](https://huggingface.co/papers/2602.02444).
 
-## Training Data
-
-This model was trained using the [MultiVENT 2.0 dataset](https://huggingface.co/datasets/hltcoe/MultiVENT2.0 ).
+- **Repository:** [https://github.com/tskow99/RANKVIDEO-Reasoning-Reranker](https://github.com/tskow99/RANKVIDEO-Reasoning-Reranker)
+- **Paper:** [RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval](https://arxiv.org/abs/2602.02444)
 
+## Training Data
 
+This model was trained using the [MultiVENT 2.0 dataset](https://huggingface.co/datasets/hltcoe/MultiVENT2.0).
 
 ## Usage
 
-```
+You can use the model for scoring query-video pairs via the `rankvideo` library as follows:
 
+```python
 from rankvideo import VLMReranker
 
 reranker = VLMReranker(model_path="hltcoe/RankVideo")
 
+# Score query-video pairs for relevance
 scores = reranker.score_batch(
     queries=["person playing guitar"],
     video_paths=["/path/to/video.mp4"],
 )
 
 print(f"Relevance score: {scores[0]['logit_delta_yes_minus_no']:.3f}")
-
 ```
+
 ## BibTeX
+
 ```bibtex
 @misc{skow2026rankvideoreasoningrerankingtexttovideo,
       title={RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval}, 
@@ -50,4 +55,5 @@ print(f"Relevance score: {scores[0]['logit_delta_yes_minus_no']:.3f}")
       archivePrefix={arXiv},
       primaryClass={cs.IR},
       url={https://arxiv.org/abs/2602.02444}, 
-}
+}
+```