Update README.md

README.md

@@ -20,7 +20,9 @@ base_model: meta-llama/Meta-Llama-3-8B
 
 This llama model was trained with Huggingface's TRL library and NEFTune https://arxiv.org/abs/2310.05914 using open-sourced finance dataset https://huggingface.co/datasets/FinLang/investopedia-instruction-tuning-dataset developed for finance application by FinLang Team
 
-This project is for research purposes only. Third-party datasets may be subject to additional terms and conditions under their associated licenses.
+NEFTune paper propose to add random noise to the embedding vectors of the training data during the forward pass of fine-tuning as a result the model overfits less to the
+specifics of the instruction-tuning dataset, such as formatting details, exact wording, and text length. Instead of collapsing to the exact instruction distribution, the model is more capable of providing
+answers that incorporate knowledge and behaviors of the pretrained base model.
 
 ## How to Get Started with the Model