Upload README.md with huggingface_hub

README.md

@@ -64,3 +64,43 @@ model.attn_backend = "flex"  # propagates to all attention layers in-place
 
 ## Embed datasets
 All DPLM models inherit `EmbeddingMixin`, so you can call `model.embed_dataset(...)` directly.
+
+## Citations
+
+```bibtex
+@article{wang2024dplm,
+  title={Diffusion Language Models Are Versatile Protein Learners},
+  author={Wang, Xinyou and Ye, Zaixiang and Huang, Fei and Cao, Dongyan and Liang, Shujian and Huang, Liang},
+  journal={Proceedings of the 41st International Conference on Machine Learning},
+  year={2024}
+}
+```
+
+```bibtex
+@misc{FastPLMs,
+  author={Hallee, Logan and Bichara, David and Gleghorn, Jason P.},
+  title={FastPLMs: Fast, efficient, protein language model inference from Huggingface AutoModel.},
+  year={2024},
+  url={https://huggingface.co/Synthyra/ESMplusplus_small},
+  DOI={10.57967/hf/3726},
+  publisher={Hugging Face}
+}
+```
+
+```bibtex
+@article{dong2024flexattention,
+  title={Flex Attention: A Programming Model for Generating Optimized Attention Kernels},
+  author={Dong, Juechu and Feng, Boyuan and Guessous, Driss and Liang, Yanbo and He, Horace},
+  journal={arXiv preprint arXiv:2412.05496},
+  year={2024}
+}
+```
+
+```bibtex
+@inproceedings{paszke2019pytorch,
+  title={PyTorch: An Imperative Style, High-Performance Deep Learning Library},
+  author={Paszke, Adam and Gross, Sam and Massa, Francisco and Lerer, Adam and Bradbury, James and Chanan, Gregory and Killeen, Trevor and Lin, Zeming and Gimelshein, Natalia and Antiga, Luca and Desmaison, Alban and K{\"o}pf, Andreas and Yang, Edward and DeVito, Zach and Raison, Martin and Tejani, Alykhan and Chilamkurthy, Sasank and Steiner, Benoit and Fang, Lu and Bai, Junjie and Chintala, Soumith},
+  booktitle={Advances in Neural Information Processing Systems 32},
+  year={2019}
+}
+```