Update README.md

README.md

@@ -9,7 +9,7 @@ base_model:
 
 ## **Pretraining on Phosphosites and their MSAs with MLM Objective on ESM-1b Architecture**
 
-This repository presents a pretrained ESM-1b architecture, where the weights are initialized **from scratch** and trained using the Masked Language Modeling (MLM) objective. The training data consists of labeled phosphosites derived from (DARKIN)[https://openreview.net/forum?id=a4x5tbYRYV] and and their Multiple Sequence Alignments (MSA).
+This repository presents a pretrained ESM-1b architecture, where the weights are initialized **from scratch** and trained using the Masked Language Modeling (MLM) objective. The training data consists of labeled phosphosites derived from [DARKIN](https://openreview.net/forum?id=a4x5tbYRYV) and and their Multiple Sequence Alignments (MSA).
 
 ### **Developed by:**
 Zeynep Işık (MSc, Sabanci University)
@@ -18,7 +18,7 @@ Zeynep Işık (MSc, Sabanci University)
 
 Architecture: ESM-1b (trained from scratch)
 Pretraining Objective: Masked Language Modeling (MLM)
-Dataset: Labeled phosphosites from (DARKIN)[https://openreview.net/forum?id=a4x5tbYRYV] and their MSAs.
+Dataset: Labeled phosphosites from [DARKIN](https://openreview.net/forum?id=a4x5tbYRYV) and their MSAs.
 Total Samples: 702,468 (10% seperated for validation)
 Sequence Length: ≤ 128 residues
 Batch Size: 64