Dongsung commited on
Commit
f05bff7
1 Parent(s): bc23b57

Update model description

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -6,6 +6,14 @@ This model contains just the `IPUConfig` files for running the BERT large model
6
 
7
  **This model contains no model weights, only an IPUConfig.**
8
 
 
 
 
 
 
 
 
 
9
  ## Usage
10
 
11
  ```
 
6
 
7
  **This model contains no model weights, only an IPUConfig.**
8
 
9
+ ## Model description
10
+
11
+ BERT (Bidirectional Encoder Representations from Transformers) is a transformers model which is designed to pretrain bidirectional representations from unlabeled texts. It enables easy and fast fine-tuning for different downstream task such as Sequence Classification, Named Entity Recognition, Question Answering, Multiple Choice and MaskedLM.
12
+
13
+ It was trained with two objectives in pretraining : Masked language modeling(MLM) and Next sentence prediction(NSP). First, MLM is different from traditional LM which sees the words one after another while BERT allows the model to learn a bidirectional representation. In addition to MLM, NSP is used for jointly pertaining text-pair representations.
14
+
15
+ It reduces the need of many engineering efforts for building task specific architectures through pre-trained representation. And achieves state-of-the-art performance on a large suite of sentence-level and token-level tasks.
16
+
17
  ## Usage
18
 
19
  ```