Update README.md

README.md

@@ -9,9 +9,10 @@ datasets:
 
 # Model Card for Llava-mnist
 
-This model is a simple linear layer vision encoder trained on the MNIST dataset, following the Llava training approach.
+Llava-mnist is a simple example of Vision and Language model using LLaVA architecture trained on MNIST dataset.
 
-You can use this model alongside [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct).
+
+You can use this model (just one linear layer vision encoder model) alongside [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct).
 
 ## Training Details