Update README.md

README.md

@@ -1,13 +1,17 @@
 ---
 license: mit
 tags:
-
-  - sentence-transformers
-  - sentence-similarity
-  - mteb
-  - retriever
-  - text-embeddings-inference
-
+- sentence-transformers
+- sentence-similarity
+- mteb
+- retriever
+- text-embeddings-inference
+language:
+- en
+- zh
+base_model:
+- Qwen/Qwen3-Embedding-0.6B
+library_name: adapter-transformers
 ---
 
 # Jasper-Token-Compression-600M
@@ -19,6 +23,10 @@ compression**. Through the combination of vector distillation and contrastive le
 10x
 while still achieving excellent performance!
 
+Original training codes: https://github.com/DunZhang/Jasper-Token-Compression-Training
+
+Report: https://arxiv.org/abs/2511.14405
+
 ## Features
 
 - ⭐⭐⭐ Supports bilingual (Chinese and English)
@@ -130,9 +138,6 @@ I only distilled texts up to 1024 tokens in length, so there should be performan
 
 If you find our work worth citing, please use the following citation.
 
-For distillation, please cite the following paper:
-**Jasper and Stella Technical Report:**
-
 ```
 
 @misc{zhang2025jasperstelladistillationsota,
@@ -147,4 +152,14 @@ For distillation, please cite the following paper:
 
 ```
 
-For text compression, please cite this link directly. We will consider writing a report later.
+```
+@misc{zhang2025jaspertokencompression600mtechnicalreport,
+      title={Jasper-Token-Compression-600M Technical Report}, 
+      author={Dun Zhang and Ziyang Zeng and Yudong Zhou and Shuyang Lu},
+      year={2025},
+      eprint={2511.14405},
+      archivePrefix={arXiv},
+      primaryClass={cs.IR},
+      url={https://arxiv.org/abs/2511.14405}, 
+}
+```