Update for paper release

README.md

@@ -11,7 +11,7 @@ license: apache-2.0
 
 **Falcon-RW-1B is a 1B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained on 350B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb). It is made available under the Apache 2.0 license.**
 
-*Paper coming soon 😊.*
+See the 📓 [paper on arXiv](https://arxiv.org/abs/2306.01116) for more details.
 
 RefinedWeb is a high-quality web dataset built by leveraging stringent filtering and large-scale deduplication. Falcon-RW-1B, trained on RefinedWeb only, matches or outperforms comparable models trained on curated data.
 
@@ -63,7 +63,7 @@ for seq in sequences:
 
 ### Model Source
 
-- **Paper:** *coming soon*.
+- **Paper:** [https://arxiv.org/abs/2306.01116](https://arxiv.org/abs/2306.01116).
 
 ## Uses
 
@@ -147,7 +147,7 @@ Training happened in early December 2022 and took about six days.
 
 ## Evaluation
 
-*Paper coming soon.*
+See the 📓 [paper on arXiv](https://arxiv.org/abs/2306.01116) for in-depth evaluation.
 
 
 ## Technical Specifications 
@@ -179,7 +179,15 @@ Falcon-RW-1B was trained a custom distributed training codebase, Gigatron. It us
 
 ## Citation
 
-*Paper coming soon 😊.*
+@article{refinedweb,
+  title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only},
+  author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay},
+  journal={arXiv preprint arXiv:2306.01116},
+  eprint={2306.01116},
+  eprinttype = {arXiv},
+  url={https://arxiv.org/abs/2306.01116},
+  year={2023}
+}
 
 
 ## Contact