Update README.md

README.md

@@ -63,7 +63,7 @@ Use the code below to get started with the model.
 
 ```python
 from transformers import pipeline
-unmasker = pipeline('fill-mask', model='bert-base-cased')
+unmasker = pipeline('fill-mask', model='bert-java-bfp_combined')
 unmasker(java_code) # Replace with Java code; Use '[MASK]' to mask tokens/words in the code.
 ```
 
@@ -81,7 +81,7 @@ The model was trained on 198088 Java methods, containing the code before and aft
 
 #### Preprocessing [optional]
 
-Remove comments and replace consecutive whitespace characters by a single space
+Remove comments and replace consecutive whitespace characters by a single space.
 
 #### Training Hyperparameters
 
@@ -115,11 +115,11 @@ The model was evaluated on 49522 Java methods, from the 20% split of the dataset
 
 <!-- These are the evaluation metrics being used, ideally with a description of why. -->
 
-[More Information Needed]
+Perplexity
 
 ### Results
 
-[More Information Needed]
+1.48
 
 #### Summary