Update README.md

README.md

@@ -17,6 +17,16 @@ library_name: Megatron-LM
 
 # InstructRetro
 
+[Documentation](https://github.com/NVIDIA/Megatron-LM/tree/InstructRetro/tools/retro)   [Paper](https://arxiv.org/abs/2310.07713)   [Evaluation Data](https://drive.google.com/drive/folders/1xw-N0LJR_lIWnH6BKzHIb49quVCS_V72?usp=drive_link)   [Model Weights](https://huggingface.co/collections/nvidia/instructretro-65837ea76b60651e01faec8d)
+
+InstructRetro [(Wang et al., 2023b)](https://arxiv.org/abs/2310.07713) scales up the size of Retro to 48B, featuring the largest LLM pretrained with retrieval (as of December 2023). 
+The obtained foundation model, Retro 48B, largely outperforms the GPT counterpart in terms of perplexity.
+With instruction tuning on Retro, InstructRetro demonstrates significant improvement over the instruction tuned GPT on downstream tasks in the zero-shot setting. Specifically, the average improvement of InstructRetro is 7% over its GPT counterpart across 8 short-form QA tasks, and 10% over GPT across 4 challenging long-form QA tasks. We also find that one can ablate the encoder from InstructRetro architecture and directly use the InstructRetro decoder backbone as GPT, while achieving comparable results.
+
+**For more information about InstructRetro, check the [Documentation](https://github.com/NVIDIA/Megatron-LM/tree/InstructRetro/tools/retro)!**
+
+## Background
+
 Retro [(Borgeaud et al., 2022)](https://arxiv.org/abs/2112.04426) is an autoregressive decoder-only language model (LM) pretrained with retrieval-augmentation. 
 Retro features practical scalibility to support large-scale pretraining from scratch by retrieving from trillions of token.
 Pretraining with retrieval provides a more efficient storage mechanism of factual knowledge, when compared to storing factual knowledge implicitly within the network's parameters, thus largely reducing model parameters while achieving lower perplexity than standard GPT. 
@@ -24,11 +34,7 @@ Retro also provides the flexibility to update the
 knowledge stored in LMs [(Wang et al., 2023a)](https://arxiv.org/abs/2304.06762)
 by updating the retrieval database without training LMs again.
 
-InstructRetro [(Wang et al., 2023b)](https://arxiv.org/abs/2310.07713) further scales up the size of Retro to 48B, featuring the largest LLM pretrained with retrieval (as of December 2023). 
-The obtained foundation model, Retro 48B, largely outperforms the GPT counterpart in terms of perplexity.
-With instruction tuning on Retro, InstructRetro demonstrates significant improvement over the instruction tuned GPT on downstream tasks in the zero-shot setting. Specifically, the average improvement of InstructRetro is 7% over its GPT counterpart across 8 short-form QA tasks, and 10% over GPT across 4 challenging long-form QA tasks. We also find that one can ablate the encoder from InstructRetro architecture and directly use the InstructRetro decoder backbone as GPT, while achieving comparable results.
-
-## Model Overview
+## Overview
 
 ### License