Add pipeline tag and link to paper/code

README.md

@@ -1,13 +1,18 @@
 ---
-license: apache-2.0
 datasets:
 - AL-GR/Item-EMB
 language:
 - zh
+license: apache-2.0
+pipeline_tag: feature-extraction
 ---
+
 # Forge-SID-Model
 
-This repository contains a pre-trained **RQVAE (Residual Quantized Variational Autoencoder)** model designed for **SID (Speaker Identity/Structure) generation** tasks. It is part of the [FORGE](https://github.com/AL-GR/FORGE) ecosystem.
+This repository contains a pre-trained **RQVAE (Residual Quantized Variational Autoencoder)** model designed for **SID (Semantic Identifier) generation** tasks. It is part of the [FORGE](https://github.com/AL-GR/FORGE) ecosystem, introduced in the paper [FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets](https://huggingface.co/papers/2509.20904).
+
+- **Project Page:** [https://huggingface.co/AL-GR](https://huggingface.co/AL-GR)
+- **Code:** [https://github.com/selous123/al_sid](https://github.com/selous123/al_sid)
 
 The model weights are stored in `final_sid_rq_model.pth`.
 
@@ -55,4 +60,17 @@ CKPT_PATH = './Forge-SID-Model/final_sid_rq_model.pth'
 
 ---
 
-For more details about the training setup or the FORGE framework, please refer to the main repository: [AL-GR/FORGE](https://github.com/AL-GR/FORGE).
+For more details about the training setup or the FORGE framework, please refer to the main repository: [AL-GR/FORGE](https://github.com/AL-GR/FORGE).
+
+## Citation
+
+If you find this work helpful, please cite:
+
+```bibtex
+@article{fu2025forge,
+  title={FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets},
+  author={Fu, Kairui and Zhang, Tao and Xiao, Shuwen and Wang, Ziyang and Zhang, Xinming and Zhang, Chenchi and Yan, Yuliang and Zheng, Junjun and others},
+  journal={arXiv preprint arXiv:2509.20904},
+  year={2025}
+}
+```