Files changed (1) hide show
  1. dslim_bert-base-NER.json +169 -0
dslim_bert-base-NER.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bomFormat": "CycloneDX",
3
+ "specVersion": "1.6",
4
+ "serialNumber": "urn:uuid:2d71328a-f87c-48dc-9f4e-ba83929b1cb0",
5
+ "version": 1,
6
+ "metadata": {
7
+ "timestamp": "2025-06-05T09:39:43.530276+00:00",
8
+ "component": {
9
+ "type": "machine-learning-model",
10
+ "bom-ref": "dslim/bert-base-NER-40551b74-59a4-53a9-ae36-e1dca4f66e41",
11
+ "name": "dslim/bert-base-NER",
12
+ "externalReferences": [
13
+ {
14
+ "url": "https://huggingface.co/dslim/bert-base-NER",
15
+ "type": "documentation"
16
+ }
17
+ ],
18
+ "modelCard": {
19
+ "modelParameters": {
20
+ "task": "token-classification",
21
+ "architectureFamily": "bert",
22
+ "modelArchitecture": "BertForTokenClassification",
23
+ "datasets": [
24
+ {
25
+ "ref": "conll2003-be67a053-25af-52ad-93c8-134501f8fa4b"
26
+ }
27
+ ]
28
+ },
29
+ "properties": [
30
+ {
31
+ "name": "library_name",
32
+ "value": "transformers"
33
+ }
34
+ ],
35
+ "quantitativeAnalysis": {
36
+ "performanceMetrics": [
37
+ {
38
+ "slice": "dataset: conll2003, split: test, config: conll2003",
39
+ "type": "accuracy",
40
+ "value": 0.9118041001560013
41
+ },
42
+ {
43
+ "slice": "dataset: conll2003, split: test, config: conll2003",
44
+ "type": "precision",
45
+ "value": 0.9211550382257732
46
+ },
47
+ {
48
+ "slice": "dataset: conll2003, split: test, config: conll2003",
49
+ "type": "recall",
50
+ "value": 0.9306415698281261
51
+ },
52
+ {
53
+ "slice": "dataset: conll2003, split: test, config: conll2003",
54
+ "type": "f1",
55
+ "value": 0.9258740048459675
56
+ },
57
+ {
58
+ "slice": "dataset: conll2003, split: test, config: conll2003",
59
+ "type": "loss",
60
+ "value": 0.48325642943382263
61
+ }
62
+ ]
63
+ }
64
+ },
65
+ "authors": [
66
+ {
67
+ "name": "dslim"
68
+ }
69
+ ],
70
+ "licenses": [
71
+ {
72
+ "license": {
73
+ "id": "MIT",
74
+ "url": "https://spdx.org/licenses/MIT.html"
75
+ }
76
+ }
77
+ ],
78
+ "description": "**bert-base-NER** is a fine-tuned BERT model that is ready to use for **Named Entity Recognition** and achieves **state-of-the-art performance** for the NER task. It has been trained to recognize four types of entities: location (LOC), organizations (ORG), person (PER) and Miscellaneous (MISC).Specifically, this model is a *bert-base-cased* model that was fine-tuned on the English version of the standard [CoNLL-2003 Named Entity Recognition](https://www.aclweb.org/anthology/W03-0419.pdf) dataset.If you'd like to use a larger BERT-large model fine-tuned on the same dataset, a [**bert-large-NER**](https://huggingface.co/dslim/bert-large-NER/) version is also available.",
79
+ "tags": [
80
+ "transformers",
81
+ "pytorch",
82
+ "tf",
83
+ "jax",
84
+ "onnx",
85
+ "safetensors",
86
+ "bert",
87
+ "token-classification",
88
+ "en",
89
+ "dataset:conll2003",
90
+ "arxiv:1810.04805",
91
+ "license:mit",
92
+ "model-index",
93
+ "autotrain_compatible",
94
+ "endpoints_compatible",
95
+ "region:us"
96
+ ]
97
+ }
98
+ },
99
+ "components": [
100
+ {
101
+ "type": "data",
102
+ "bom-ref": "conll2003-be67a053-25af-52ad-93c8-134501f8fa4b",
103
+ "name": "conll2003",
104
+ "data": [
105
+ {
106
+ "type": "dataset",
107
+ "bom-ref": "conll2003-be67a053-25af-52ad-93c8-134501f8fa4b",
108
+ "name": "conll2003",
109
+ "contents": {
110
+ "url": "https://huggingface.co/datasets/conll2003",
111
+ "properties": [
112
+ {
113
+ "name": "task_categories",
114
+ "value": "token-classification"
115
+ },
116
+ {
117
+ "name": "task_ids",
118
+ "value": "named-entity-recognition, part-of-speech"
119
+ },
120
+ {
121
+ "name": "language",
122
+ "value": "en"
123
+ },
124
+ {
125
+ "name": "size_categories",
126
+ "value": "10K<n<100K"
127
+ },
128
+ {
129
+ "name": "annotations_creators",
130
+ "value": "crowdsourced"
131
+ },
132
+ {
133
+ "name": "language_creators",
134
+ "value": "found"
135
+ },
136
+ {
137
+ "name": "pretty_name",
138
+ "value": "CoNLL-2003"
139
+ },
140
+ {
141
+ "name": "source_datasets",
142
+ "value": "extended|other-reuters-corpus"
143
+ },
144
+ {
145
+ "name": "paperswithcode_id",
146
+ "value": "conll-2003"
147
+ },
148
+ {
149
+ "name": "license",
150
+ "value": "other"
151
+ }
152
+ ]
153
+ },
154
+ "governance": {
155
+ "owners": [
156
+ {
157
+ "organization": {
158
+ "name": "eriktks",
159
+ "url": "https://huggingface.co/eriktks"
160
+ }
161
+ }
162
+ ]
163
+ },
164
+ "description": "The shared task of CoNLL-2003 concerns language-independent named entity recognition. We will concentrate on\nfour types of named entities: persons, locations, organizations and names of miscellaneous entities that do\nnot belong to the previous three groups.\n\nThe CoNLL-2003 shared task data files contain four columns separated by a single space. Each word has been put on\na separate line and there is an empty line after each sentence. The first item on each line is a word, the second\na part-of-speech (POS) tag, the third a syntactic chunk tag and the fourth the named entity tag. The chunk tags\nand the named entity tags have the format I-TYPE which means that the word is inside a phrase of type TYPE. Only\nif two phrases of the same type immediately follow each other, the first word of the second phrase will have tag\nB-TYPE to show that it starts a new phrase. A word with tag O is not part of a phrase. Note the dataset uses IOB2\ntagging scheme, whereas the original dataset uses IOB1.\n\nFor more details see https://www.clips.uantwerpen.be/conll2003/ner/ and https://www.aclweb.org/anthology/W03-0419"
165
+ }
166
+ ]
167
+ }
168
+ ]
169
+ }