Update README.md

README.md

@@ -19,12 +19,12 @@ model = BertForMaskedLM.from_pretrained(model_name)
 tokenizer = BertTokenizer.from_pretrained(model_name)
 ````
 
-To use it on a sentence :
+To use it as a masked language model :
 
 ````python
 import torch
 
-sentence = "The goal of life is [MASK]."
+sentence = "Let's have a [MASK]."
 
 encoded_inputs = tokenizer([sentence], padding='longest')
 input_ids = torch.tensor(encoded_inputs['input_ids'])
@@ -37,3 +37,17 @@ predicted_token = tokenizer.decode(masked_token)
 
 print(predicted_token)
 ````
+
+Or we can also predict the n most relevant predictions :
+
+````python
+top_n = 5
+
+vocab_size = model.config.vocab_size
+logits = output['logits'][0][mask_index].tolist()
+top_tokens = sorted(list(range(vocab_size)), key=lambda  i:logits[i], reverse=True)[:top_n]
+
+tokenizer.decode(top_tokens)
+````
+
+