Update model description

README.md

@@ -6,6 +6,11 @@ This model contains just the `IPUConfig` files for running the [gpt2](https://hu
 
 **This model contains no model weights, only an IPUConfig.** 
 
+## Model description
+GPT2 is a large transformer-based language model. It is built using transformer decoder blocks. BERT, on the other hand, uses transformer encoder blocks. It adds Layer normalisation to the input of each sub-block, similar to a pre-activation residual networks and an additional layer normalisation.  
+ 
+Paper link : [Language Models are Unsupervised Multitask Learners](https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf) 
+
 ## Usage
 
 ```