update readme so that model will be linked to paper

README.md

@@ -25,6 +25,7 @@ These are model checkpoints and LoRA adapters from the research paper ["LoRA Lea
 - **Language(s) (NLP):** English
 - **License:** cc-by-nc-4.0
 - **Finetuned from model:** Llama-2-7b
+- **Paper:** [arxiv.org/abs/2405.09673](https://arxiv.org/abs/2405.09673)
 
 We trained [Llama-2-7B](https://huggingface.co/meta-llama/Llama-2-7b-hf) using full finetuning and LoRA. Model checkpoints and LoRA adapters can be found on HuggingFace here: [LoRA-TMLR-2024](https://huggingface.co/LoRA-TMLR-2024). Intermediate checkpoints can be found in the branches of the respective models.