Update README.md

README.md

@@ -20,6 +20,10 @@ NeuralBeagle14-7B is a DPO fine-tune of [mlabonne/Beagle14-7B](https://huggingfa
 
 Thanks [Argilla](https://huggingface.co/argilla) for providing the dataset and the training recipe [here](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp). 💪
 
+## 🔍 Usage
+
+This model uses a context window of 8k. Compared to other 7B models, it displays good performance in instruction following and reasoning tasks. It can also be used for RP and storytelling.
+
 ## 🏆 Evaluation
 
 The evaluation was performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval) on Nous suite. It is the best 7B model to date.