README.md in libmf-0.2.0 vs README.md in libmf-0.2.1

@@ -2,11 +2,11 @@
 
 [LIBMF](https://github.com/cjlin1/libmf) - large-scale sparse matrix factorization - for Ruby
 
 Check out [Disco](https://github.com/ankane/disco) for higher-level collaborative filtering
 
-[![Build Status](https://travis-ci.org/ankane/libmf.svg?branch=master)](https://travis-ci.org/ankane/libmf) [![Build status](https://ci.appveyor.com/api/projects/status/92fbip1bd8sjd2tj/branch/master?svg=true)](https://ci.appveyor.com/project/ankane/libmf/branch/master)
+[![Build Status](https://github.com/ankane/libmf/workflows/build/badge.svg?branch=master)](https://github.com/ankane/libmf/actions)
 
 ## Installation
 
 Add this line to your application’s Gemfile:
 
@@ -37,15 +37,20 @@
 
 ```ruby
 model.predict(row_index, column_index)
 ```
 
-Get the bias and latent factors
+Get the latent factors (these approximate the training matrix)
 
 ```ruby
-model.bias
 model.p_factors
 model.q_factors
+```
+
+Get the bias (average of all elements in the training matrix)
+
+```ruby
+model.bias
 ```
 
 Save the model to a file
 
 ```ruby