Update README.md

README.md

@@ -19,11 +19,11 @@ Access to [git](https://github.com/yarongef/DistilProtBert)
 DistilProtBert was pretrained on millions of proteins sequences. 
 
 Differences between DistilProtBert model and ProtBert:
-1. Size of the model: 
-    - 230M parameters (420M parameters in ProtBert)
-    - 15 hidden layers (30 hidden layers in ProtBert)
-2. Size of the pretraining dataset: ~43M proteins (ProtBert was pretrained on 216M proteins)
-3. Hardware used for pretraining: five v100 32GB Nvidia GPUs (ProtBert was pretrained on 512 16GB TPUs) 
+
+|    **Model**   | **Parameters** | **Hidden layers** | **Pretraining sequences** | **Pretraining hardware** |
+|:--------------:|:--------------:|:-----------------:|:-------------------------:|:------------------------:|
+|    ProtBert    |      420M      |         30        |            43M            |     5 v100 32GB GPUs     |
+| DistilProtBert |      230M      |         15        |            216M           |       512 16GB Tpus      |
 
 ## Intended uses & limitations