diff --git a/README.md b/README.md
index 58b67f80..21552f14 100644
--- a/README.md
+++ b/README.md
@@ -1731,6 +1731,7 @@
 #### [Manifold Diffusion Fields](summaries/2305.15586.md)
 #### [QLoRA: Efficient Finetuning of Quantized LLMs](summaries/2305.14314.md)
 #### [Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization](summaries/2305.14152.md)
+#### [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](summaries/2305.13245.md)
 #### [RWKV: Reinventing RNNs for the Transformer Era](summaries/2305.13048.md)
 #### [Accurate Knowledge Distillation with n-best Reranking](summaries/2305.12057.md)
 #### [LLM-Pruner: On the Structural Pruning of Large Language Models](summaries/2305.11627.md)
diff --git a/summaries/2305.13245.md b/summaries/2305.13245.md
new file mode 100644
index 00000000..e93fd2b2
--- /dev/null
+++ b/summaries/2305.13245.md
@@ -0,0 +1,5 @@
+# GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
+## TL;DR
+## Summary
+- [https://arxiv.org/pdf/2305.13245.pdf](https://arxiv.org/pdf/2305.13245.pdf)
+