Update README.md

README.md

@@ -1,3 +1,38 @@
----
-license: cc-by-4.0
----
+---
+license: mit
+---
+
+# Probing Visual Language Priors in VLMs
+
+
+## ImageDPO Finetuned Model  
+
+This page provides the **ImageDPO** finetuned checkpoint for LLaVA-v1.5-7B used in [Probing Visual Language Priors in VLMs](https://arxiv.org/abs/2501.00569). We offer the **merged model weights** for use.  
+
+## Usage  
+
+First, install the [LLaVA-v1.5 codebase](https://github.com/LLaVA-VL/LLaVA-Plus-Codebase).    
+
+Run the following command to have a try:
+
+```bash
+python -m llava.eval.run_llava \
+    --model-path ViLP/LLaVA-v1.5-7b-ImageDPO \
+    --image-file 'images/llava_logo.png' \
+    --query 'Please caption this image.' \
+    --conv-mode llava_v1
+```
+
+
+## Citation Information
+
+Please cite ***ViLP*** paper accordingly, if you find our resource helpful!
+
+```bibtex
+@article{luo2024probing,
+      title={Probing Visual Language Priors in VLMs},
+      author={Luo, Tiange and Cao, Ang and Lee, Gunhee and Johnson, Justin and Lee, Honglak},
+      journal={arXiv preprint arXiv:2501.00569},
+      year={2024}
+}
+```