lysandre HF staff commited on
Commit
961be02
1 Parent(s): 8729e56

Update dimensions

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -40,6 +40,14 @@ This way, the model learns an inner representation of the English language that
40
  useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
41
  classifier using the features produced by the BERT model as inputs.
42
 
 
 
 
 
 
 
 
 
43
  ## Intended uses & limitations
44
 
45
  You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
 
40
  useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
41
  classifier using the features produced by the BERT model as inputs.
42
 
43
+
44
+ This model has the following configuration:
45
+
46
+ - 24-layer
47
+ - 1024 hidden dimension
48
+ - 16 attention heads
49
+ - 336M parameters.
50
+
51
  ## Intended uses & limitations
52
 
53
  You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to