Update README.md

README.md

@@ -8,35 +8,35 @@ 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.
-
-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
+  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
 
 
 
 2. Protein Sequence Completion:
-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:
-
-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"
+  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:
+  
+  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"