Update README.md

README.md

@@ -8,3 +8,32 @@ The weights of the model were initialized from scratch.
 
 PS : the tokenizer is the same as the one of the model bert-base-uncased.
 
+
+To load the model \& tokenizer :
+
+````python
+from transformers import BertForMaskedLM, BertTokenizer
+
+model_name = "eli4s/Bert-L12-h240-A12"
+model = BertForMaskedLM.from_pretrained(model_name)
+tokenizer = BertTokenizer.from_pretrained(model_name)
+````
+
+To use it on a sentence :
+
+````python
+import torch
+
+sentence = "The goal of life is [MASK]."
+
+encoded_inputs = tokenizer([sentence], padding='longest')
+input_ids = torch.tensor(encoded_inputs['input_ids'])
+attention_mask = torch.tensor(encoded_inputs['attention_mask'])
+output = model(input_ids, attention_mask=attention_mask)
+
+mask_index = input_ids.tolist()[0].index(103)
+masked_token = output['logits'][0][mask_index].argmax(axis=-1)
+predicted_token = tokenizer.decode(masked_token)
+
+print(predicted_token)
+````