Create README.md

README.md

@@ -0,0 +1,18 @@
+# RecGPT: Generative  Pre-training  for  Text-based  Recommendation
+
+We present the first domain-adapted and fully-trained large language model,  RecGPT-7B, and its instruction-following variant, RecGPT-7B-Instruct, for  text-based  recommendation. Experimental results on rating prediction and  sequential recommendation tasks show that our model, RecGPT-7B-Instruct,  outperforms previous strong baselines. The general architecture and experimental results of RecGPT can be found in our [paper](arxivlink):
+
+```
+@inproceedings{RecGPT,
+title     = {{RecGPT: Generative Pre-training for Text-based Recommendation}},
+author    = {Hoang Ngo and Dat Quoc Nguyen},
+booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics},
+year      = {2024}
+}
+```
+
+We publicly release the RecGPT models along with their pre-training and fine-tuning datasets. 
+
+Please cite our paper whenever RecGPT or the datasets are used to help produce published results or are incorporated into other software. 
+
+For further information or requests, please go to [RecGPT's homepage](https://github.com/VinAIResearch/RecGPT)!