Update README.md

README.md

@@ -5773,6 +5773,11 @@ It is built upon the [gte-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/
 
 - **Top-tier performance**: **INF-Retriever-v1** has achieved outstanding results on the AIR-Bench leaderboard, making it a top choice for heterogeneous information retrieval tasks across various domains.
 
+## Model Details
+- Model Size: 7B
+- Embedding Dimension: 3584
+- Max Input Tokens: 32768
+
 ## Usage
 
 ### Sentence Transformers
@@ -5885,4 +5890,18 @@ Although INF-Retriever-v1 has been fine-tuned exclusively on English and Chinese
 ### Supervisors
 Wei Chu • Yinghui Xu • Yuan Qi
 ### INF memory team
-Junhan Yang ([email protected]) • Jiahe Wan • Yichen Yao ([email protected])
+Junhan Yang ([email protected]) • Jiahe Wan • Yichen Yao ([email protected])
+
+## Citation
+If you find our model useful, please consider citing:
+
+```
+@misc {infly-ai_2025,
+	author       = { {infly-ai} },
+	title        = { inf-retriever-v1 (Revision 5f469d7) },
+	year         = 2025,
+	url          = { https://huggingface.co/infly/inf-retriever-v1 },
+	doi          = { 10.57967/hf/4262 },
+	publisher    = { Hugging Face }
+}
+```