Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+asset/demos.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model:
+- google/siglip2-so400m-patch14-384
+---
+### Unifying Visual Understanding and Generation via Text-Aligned Representations
+> [Jiaming Han](https://csuhan.com), [Hao Chen](https://haochen-rye.github.io)<sup>†</sup>, [Yang Zhao](https://scholar.google.com/citations?user=uPmTOHAAAAAJ&hl=zh-CN), [Hanyu Wang](https://hywang66.github.io), [Qi Zhao](https://kevinz8866.github.io), [Ziyan Yang](https://ziyanyang.github.io), [Hao He](https://hehao13.github.io), [Xiangyu Yue](https://xyue.io)<sup>‡</sup>, [Lu Jiang](https://www.lujiang.info)<sup>‡</sup>
+>
+> <sup>†</sup> Project Lead&nbsp;&nbsp;<sup>‡</sup> Corresponding Authors
+
+ <a href="https://tar.csuhan.com">
+    <img
+      src="https://img.shields.io/badge/Project-Page-0A66C2?logo=chromewebstore&logoColor=0A66C2"
+      alt="Project Page"
+    />
+  </a>
+<a href="http://arxiv.org/abs/2506.18898">
+    <img
+      src="https://img.shields.io/badge/arXiv-Paper-red?logo=arxiv&logoColor=red"
+      alt="Tar Paper on arXiv"
+    />
+  </a>
+  <a href="https://huggingface.co/collections/csuhan/tar-68538273b5537d0bee712648">
+    <img 
+        src="https://img.shields.io/badge/HF-Model-yellow?logo=huggingface&logoColor=yellow" 
+        alt="Huggingface Model"
+    />
+  </a>
+  <a href="https://huggingface.co/spaces/csuhan/Tar-7B">
+    <img 
+        src="https://img.shields.io/badge/HF-Space1-yellow?logo=huggingface&logoColor=yellow" 
+        alt="Huggingface Space"
+    />
+  </a>
+  <a href="https://huggingface.co/spaces/csuhan/Tar">
+    <img 
+        src="https://img.shields.io/badge/HF-Space2-yellow?logo=huggingface&logoColor=yellow" 
+        alt="Huggingface Space"
+    />
+  </a>
+
+
+<img src="asset/demos.png" width="80%">
+
+
+### Citation
+```
+@article{han2025tar,
+  title={Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations}, 
+  author={Han, Jiaming and Chen, Hao and Zhao, Yang and Wang, Hanyu and Zhao, Qi and Yang, Ziyan and He, Hao and Yue, Xiangyu and Jiang, Lu},
+  journal={arXiv preprint arXiv:2506.18898},
+  year={2025},
+}
+```
+
+### License
+This project is licensed under the Apache 2.0 License.
+

ar_dtok_lp_1024px.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7f00ed00ed03c4392d7461952b668397abd5be599065c6fd2e5f8cfef280fb
+size 2636714038

ar_dtok_lp_256px.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9108c7e2541cf692d0fb420daa2d6d1c6338daafd848182aedb3ec91d42f99
+size 2617052138

ar_dtok_lp_512px.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23f316daf4bb70c3b234ffbe66272eff862b1feb8ed468f23a5eb956779284e
+size 2620985178

ta_tok.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:933eca4cecc3f71df7b4bde62af361b844fd39e27a18d7eb7b07e9ca552b48e5
+size 2364302828