Add paper link and pipeline metadata

Hi! I'm Niels from the Hugging Face community team.

I've opened this PR to improve the model card for TAMA-QWen3. This includes:
- Adding the `pipeline_tag: table-question-answering` to help users discover the model.
- Adding `library_name: transformers` to enable the code snippet and "Use in Transformers" button.
- Linking the model to its research paper: [MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark](https://huggingface.co/papers/2506.05587).
- Including a link to the official GitHub repository for the MMTU benchmark.

These updates will make the model more discoverable and provide better documentation for researchers.

Files changed (1) hide show

README.md +12 -2

README.md CHANGED Viewed

@@ -1,5 +1,16 @@
 ---
 license: apache-2.0
 ---
 <!doctype html>
@@ -319,5 +330,4 @@ license: apache-2.0
     <p id="ref4">[4] <a href="https://arxiv.org/abs/2411.02059">Su, Aofeng, et al. "TableGPT2: A Large Multimodal Model with Tabular Data Integration." arXiv:2411.02059 (2024).</a></p>
   </div>
 </body>
-</html>

 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: table-question-answering
+---
+# TAMA-QWen3
+This model was presented in the paper [MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark](https://huggingface.co/papers/2506.05587).
+- **GitHub Repository:** [https://github.com/mmtu-benchmark/mmtu](https://github.com/mmtu-benchmark/mmtu)
+- **Paper:** [arXiv:2506.05587](https://arxiv.org/abs/2506.05587)
 ---
 <!doctype html>
     <p id="ref4">[4] <a href="https://arxiv.org/abs/2411.02059">Su, Aofeng, et al. "TableGPT2: A Large Multimodal Model with Tabular Data Integration." arXiv:2411.02059 (2024).</a></p>
   </div>
 </body>
+</html>