Update README.md

README.md

@@ -1,3 +1,22 @@
 ---
 license: apache-2.0
 ---
+
+# VCoder-DS LLaVA-1.5-7b
+
+VCoder-DS LLaVA-1.5-7b was trained on COST training dataset in December 2023. It uses the pretrained [LLaVA-1.5-7b](https://huggingface.co/liuhaotian/llava-v1.5-7b) model weights. It was introduced by Jain et al. in [this repository](https://github.com/SHI-Labs/VCoder).
+
+VCoder is an adapter for improving existing Vision LLMs at object-level perception tasks with the use of perception modalities as control inputs while retaining performance on other tasks.
+
+![img](https://praeclarumjj3.github.io/vcoder/vcoder.svg)
+
+### Citation
+
+```bibtex
+@article{jain2023vcoder,
+    title={{VCoder: Versatile Visual Encoder for Accurate Object-Level Perception with Large Language Models}},
+    author={Jitesh Jain and Jianwei Yang and Humphrey Shi},
+    journal={arXiv},
+    year={2023}
+}
+```