Add model sources and citation

README.md

@@ -14,8 +14,8 @@ Silkie is a visual language model trained using preference distillation on GPT-4
 
 - **Project page:** https://vlf-silkie.github.io/
 - **Dataset:** https://huggingface.co/datasets/MMInstruction/VLFeedback
-- **Paper:** Coming soon.
-- **Repository:** Coming soon.
+- **Paper:** https://arxiv.org/abs/2312.10665
+- **Repository:** https://github.com/vlf-silkie/VLFeedback
 
 ## Uses
 
@@ -25,7 +25,7 @@ Silkie is intended for research purposes, particularly for alignment research in
 
 ## How to Get Started
 
-Below is a simple Python code snippet to get started with the model.
+Below is a simple Python code snippet to get started with the model. For installation instructions please refer to our [Github repository](https://github.com/vlf-silkie/VLFeedback?tab=readme-ov-file#installation).
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -48,5 +48,10 @@ response, history = model.chat(tokenizer, query=query, history=None)
 ## Citation
 
 ```
-Coming soon.
+@article{2023vlfeedback,
+  author      = {Lei Li and Zhihui Xie and Mukai Li and Shunian Chen and Peiyi Wang and Liang Chen and  Yazheng Yang and  Benyou Wang and  Lingpeng Kong},
+  title       = {Silkie: Preference Distillation for Large Visual Language Models},
+  publisher   = {arXiv:2312.10665},
+  year        = {2023}
+}
 ```