Update README.md

README.md

@@ -12,6 +12,8 @@ library_name: transformers
 
 **Fanar-1-9B-Instruct** is a powerful Arabic-English LLM developed by [Qatar Computing Research Institute (QCRI)](https://www.hbku.edu.qa/en/qcri) and [Hamad Bin Khalifa University (HBKU)](https://www.hbku.edu.qa/). It is the instruction-tuned version of [Fanar-1-9B](). Built on top of `google/gemma-2-9b`, Fanar is further pretrained on 1T Arabic and English tokens. Fanar pays particular attention to the richness of the Arabic language by supporting a diverse set of Arabic dialects including Modern Standard Arabic (MSA), Levantine, and Egyptian. Fanar, through meticulous curation of the pretraining and instruction-tuning data, is aligned with Arab cultural values.
 
+We have published a comprehensive [report](https://arxiv.org/pdf/2501.13944) with all the details regarding FANAR.
+
 ---
 
 ## Model Details
@@ -36,12 +38,10 @@ library_name: transformers
 
 ## Model Training
 
-Additional dataset and training details can be found in our [report](https://arxiv.org/pdf/2501.13944).
-
-### Pretraining
+#### Pretraining
 Fanar was continually pretrained on 1T tokens, with a balanced focus on Arabic and English: 450B English tokens from a carefully curated subset of the [Dolma](https://huggingface.co/datasets/allenai/dolma) dataset, 450B Arabic tokens that we collected, parsed, and flitered from a variety of sources, 100B code tokens curated from [The Stack](https://github.com/bigcode-project/the-stack-v2) dataset. Our codebase used the [LitGPT](https://github.com/Lightning-AI/litgpt) framework. 
 
-### Post-training
+#### Post-training
 Fanar underwent a two-phase post-training pipeline:
 
 | Phase | Method | Size |