Update README.md
Browse files
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 |
|