Updated Readme

README.md

@@ -20,6 +20,9 @@ pipeline_tag: text-generation
 
 This repo contains 4-bit quantized (using AutoAWQ) model of Meta's meta-llama/Llama-2-7b-chat-hf
 
+AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration is developed by MIT-HAN-Lab
+
+
 ## Model Details
 
 - Model creator: [Meta](https://huggingface.co/meta-llama)
@@ -28,7 +31,16 @@ This repo contains 4-bit quantized (using AutoAWQ) model of Meta's meta-llama/Ll
 
 ### About 4 bit quantization using AutoAWQ
 
-AutoAWS github repo: [bitsandbytes github repo](https://github.com/casper-hansen/AutoAWQ/tree/main)
+AutoAWQ github repo: [AutoAWQ github repo](https://github.com/casper-hansen/AutoAWQ/tree/main)
+MIT-han-lab llm-aws github repo:  [MIT-han-lab llm-aws github repo](https://github.com/mit-han-lab/llm-awq/tree/main)
+
+@inproceedings{lin2023awq,
+  title={AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration},
+  author={Lin, Ji and Tang, Jiaming and Tang, Haotian and Yang, Shang and Chen, Wei-Ming and Wang, Wei-Chen and Xiao, Guangxuan and Dang, Xingyu and Gan, Chuang and Han, Song},
+  booktitle={MLSys},
+  year={2024}
+}
+
 
 # How to Get Started with the Model