Update README.md

README.md

@@ -33,7 +33,7 @@ This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmst
 
 ## Model Architecture
 
-We adjust the Llama 2 architecture for a total of around 1.8b parameters. We use the original Llama 2 tokenizer with a vocabulary size of 32,000 and train our model up to a context length of 16,384. We incorporate the sliding window attention from mistral with a size of 4,096.
+We adjust the Llama 2 architecture for a total of around 1.8b parameters. For details, please refer to our [Technical Report](https://arxiv.org/abs/2401.16818). We use the original Llama 2 tokenizer with a vocabulary size of 32,000 and train our model up to a context length of 16,384. We incorporate the sliding window attention from mistral with a size of 4,096.
 
 The details of the model architecture are: