Improve model card: Add PTQ4VM paper, pipeline tag, and library

README.md

@@ -1,13 +1,15 @@
 ---
 license: apache-2.0
+pipeline_tag: image-classification
+library_name: pytorch
 ---
 
-
-
 <br>
 
 # Vim Model Card
 
+This repository contains the model based on the paper [PTQ4VM: Post-Training Quantization for Visual Mamba](https://huggingface.co/papers/2412.20386).
+
 ## Model Details
 
 Vision Mamba (Vim) is a generic backbone trained on the ImageNet-1K dataset for vision tasks.
@@ -16,6 +18,8 @@ Vision Mamba (Vim) is a generic backbone trained on the ImageNet-1K dataset for
 - **Model type:** A generic vision backbone based on the bidirectional state space model (SSM) architecture.
 - **License:** Non-commercial license
 
+### Github repository:
+https://github.com/YoungHyun197/ptq4vm
 
 ### Model Sources
 
@@ -55,4 +59,11 @@ Vim-tiny is evaluated on ImageNet-1K val set, and achieves 76.1% Top-1 Acc. By f
 }
 ```
 
-
+```
+@article{cho2024ptq4vm,
+  title={PTQ4VM: Post-Training Quantization for Visual Mamba},
+  author={Cho, Younghyun and Lee, Changhun and Kim, Seonggon and Park, Eunhyeok},
+  journal={arXiv preprint arXiv:2412.20386},
+  year={2024}
+}
+```