MUmairAB commited on
Commit
8b1e3d1
1 Parent(s): 48040bb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -35,6 +35,7 @@ It achieves the following results on the evaluation set:
35
  ## Model description
36
 
37
  Model: "tf_bert_for_token_classification"
 
38
  _________________________________________________________________
39
  Layer (type) Output Shape Param #
40
  =================================================================
@@ -49,6 +50,7 @@ Total params: 107,726,601
49
  Trainable params: 107,726,601
50
  Non-trainable params: 0
51
  _________________________________________________________________
 
52
 
53
  ## Intended uses & limitations
54
 
@@ -62,6 +64,7 @@ This model can be used for named entity recognition tasks. It is trained on [Con
62
 
63
  The model is evaluated on [seqeval](https://github.com/chakki-works/seqeval) metric and the result is as follows:
64
 
 
65
  {'LOC': {'precision': 0.9655361050328227,
66
  'recall': 0.9608056614044638,
67
  'f1': 0.9631650750341064,
@@ -82,6 +85,7 @@ The model is evaluated on [seqeval](https://github.com/chakki-works/seqeval) met
82
  'overall_recall': 0.9527095254123191,
83
  'overall_f1': 0.944996244053084,
84
  'overall_accuracy': 0.9864013657502796}
 
85
 
86
  ## Training procedure
87
 
 
35
  ## Model description
36
 
37
  Model: "tf_bert_for_token_classification"
38
+ ```
39
  _________________________________________________________________
40
  Layer (type) Output Shape Param #
41
  =================================================================
 
50
  Trainable params: 107,726,601
51
  Non-trainable params: 0
52
  _________________________________________________________________
53
+ ```
54
 
55
  ## Intended uses & limitations
56
 
 
64
 
65
  The model is evaluated on [seqeval](https://github.com/chakki-works/seqeval) metric and the result is as follows:
66
 
67
+ ```
68
  {'LOC': {'precision': 0.9655361050328227,
69
  'recall': 0.9608056614044638,
70
  'f1': 0.9631650750341064,
 
85
  'overall_recall': 0.9527095254123191,
86
  'overall_f1': 0.944996244053084,
87
  'overall_accuracy': 0.9864013657502796}
88
+ ```
89
 
90
  ## Training procedure
91