Update README.md

README.md

@@ -8,32 +8,36 @@ Ankh3 is a protein language model that is jointly optimized on two objectives:
 * Protein sequence completion.
 
 1. Masked Language Modeling:
-  The idea of this task is to intentionally 'corrupt' an input protein sequence by
-  masking a certain percentage (X%) of its individual tokens (amino acids),
-  and then train the model to reconstruct the original sequence.
+  - The idea of this task is to intentionally 'corrupt' an input protein sequence by
+    masking a certain percentage (X%) of its individual tokens (amino acids),
+    and then train the model to reconstruct the original sequence.
   
-  Example on a protein sequence before and after corruption:
-  Original protein sequence: MKAYVLINSRGP
-  
-  This sequence will be masked/corrupted using sentinel tokens as shown below:
-  Sequence after corruption: M <extra_id_0> A Y <extra_id_1> L I <extra_id_2> S R G <extra_id_3>
-  
-  The decoder learns to correspond each sentinel token to the actual amino acid that was masked.
-  In this example: <extra_id_0> K means that <extra_id_0> corresponds to the "K" amino acid and so on.
-  Decoder output: <extra_id_0> K <extra_id_1> V <extra_id_2> N <extra_id_3> P
+  - Example on a protein sequence before and after corruption:
+
+    Original protein sequence: MKAYVLINSRGP
+
+    This sequence will be masked/corrupted using sentinel tokens as shown below:
+    Sequence after corruption: M <extra_id_0> A Y <extra_id_1> L I <extra_id_2> S R G <extra_id_3>
+
+
+    The decoder learns to correspond each sentinel token to the actual amino acid that was masked.
+    In this example: <extra_id_0> K means that <extra_id_0> corresponds to the "K" amino acid and so on.
+
+    Decoder output: <extra_id_0> K <extra_id_1> V <extra_id_2> N <extra_id_3> P
 
 
 
 2. Protein Sequence Completion:
-  The idea of this task is to cut the input sequence into
+- The idea of this task is to cut the input sequence into
   two segments, where the first segment is fed to the encoder
   and the decoder is tasked to auto-regressively generate the
   second segment conditioned on the first segment representation
   outputted from the encoder.
-  
-  Example on protein sequence completion:
-  
+
+- Example on protein sequence completion:
+
   Original sequence: MKAYVLINSRGP
+
   We will pass "MKAYVL" of it to the encoder, and the decoder is trained
   that given the representation of the first part provided by the encoder,
   it should output the second part which is: "INSRGP"