tomaarsen HF staff commited on
Commit
4b8af05
1 Parent(s): d9354e3

Upload model

Browse files
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: span-marker
3
+ tags:
4
+ - span-marker
5
+ - token-classification
6
+ - ner
7
+ - named-entity-recognition
8
+ - generated_from_span_marker_trainer
9
+ metrics:
10
+ - precision
11
+ - recall
12
+ - f1
13
+ widget: []
14
+ pipeline_tag: token-classification
15
+ ---
16
+
17
+ # SpanMarker
18
+
19
+ This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for Named Entity Recognition.
20
+
21
+ ## Model Details
22
+
23
+ ### Model Description
24
+
25
+ - **Model Type:** SpanMarker
26
+ <!-- - **Encoder:** [Unknown](https://huggingface.co/models/unknown) -->
27
+ - **Maximum Sequence Length:** 256 tokens
28
+ - **Maximum Entity Length:** 8 words
29
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
30
+ <!-- - **Language:** Unknown -->
31
+ <!-- - **License:** Unknown -->
32
+
33
+ ### Model Sources
34
+
35
+ - **Repository:** [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER)
36
+ - **Thesis:** [SpanMarker For Named Entity Recognition](https://raw.githubusercontent.com/tomaarsen/SpanMarkerNER/main/thesis.pdf)
37
+
38
+ ## Uses
39
+
40
+ ### Direct Use for Inference
41
+
42
+ ```python
43
+ from span_marker import SpanMarkerModel
44
+
45
+ # Download from the 🤗 Hub
46
+ model = SpanMarkerModel.from_pretrained("span_marker_model_id")
47
+ # Run inference
48
+ entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
49
+ ```
50
+
51
+ ### Downstream Use
52
+ You can finetune this model on your own dataset.
53
+
54
+ <details><summary>Click to expand</summary>
55
+
56
+ ```python
57
+ from span_marker import SpanMarkerModel, Trainer
58
+
59
+ # Download from the 🤗 Hub
60
+ model = SpanMarkerModel.from_pretrained("span_marker_model_id")
61
+
62
+ # Specify a Dataset with "tokens" and "ner_tag" columns
63
+ dataset = load_dataset("conll2003") # For example CoNLL2003
64
+
65
+ # Initialize a Trainer using the pretrained model & dataset
66
+ trainer = Trainer(
67
+ model=model,
68
+ train_dataset=dataset["train"],
69
+ eval_dataset=dataset["validation"],
70
+ )
71
+ trainer.train()
72
+ trainer.save_model("span_marker_model_id-finetuned")
73
+ ```
74
+ </details>
75
+
76
+ <!--
77
+ ### Out-of-Scope Use
78
+
79
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
80
+ -->
81
+
82
+ <!--
83
+ ## Bias, Risks and Limitations
84
+
85
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
86
+ -->
87
+
88
+ <!--
89
+ ### Recommendations
90
+
91
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
92
+ -->
93
+
94
+ ## Training Details
95
+
96
+ ### Framework Versions
97
+
98
+ - Python: 3.9.16
99
+ - SpanMarker: 1.3.1.dev
100
+ - Transformers: 4.33.0
101
+ - PyTorch: 2.0.1+cu118
102
+ - Datasets: 2.14.0
103
+ - Tokenizers: 0.13.2
104
+
105
+ ## Citation
106
+
107
+ ### BibTeX
108
+ ```
109
+ @software{Aarsen_SpanMarker,
110
+ author = {Aarsen, Tom},
111
+ license = {Apache-2.0},
112
+ title = {{SpanMarker for Named Entity Recognition}},
113
+ url = {https://github.com/tomaarsen/SpanMarkerNER}
114
+ }
115
+ ```
116
+
117
+ <!--
118
+ ## Glossary
119
+
120
+ *Clearly define terms in order to be accessible across audiences.*
121
+ -->
122
+
123
+ <!--
124
+ ## Model Card Authors
125
+
126
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
127
+ -->
128
+
129
+ <!--
130
+ ## Model Card Contact
131
+
132
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
133
+ -->
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<end>": 30523,
3
+ "<start>": 30522
4
+ }
config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models\\tomaarsen\\span-marker-bert-base-uncased-sourcedata\\checkpoint-final",
3
+ "architectures": [
4
+ "SpanMarkerModel"
5
+ ],
6
+ "encoder": {
7
+ "_name_or_path": "bert-base-uncased",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "BertForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": null,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": null,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "gradient_checkpointing": false,
30
+ "hidden_act": "gelu",
31
+ "hidden_dropout_prob": 0.1,
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "O",
35
+ "1": "B-SMALL_MOLECULE",
36
+ "2": "I-SMALL_MOLECULE",
37
+ "3": "B-GENEPROD",
38
+ "4": "I-GENEPROD",
39
+ "5": "B-SUBCELLULAR",
40
+ "6": "I-SUBCELLULAR",
41
+ "7": "B-CELL_TYPE",
42
+ "8": "I-CELL_TYPE",
43
+ "9": "B-TISSUE",
44
+ "10": "I-TISSUE",
45
+ "11": "B-ORGANISM",
46
+ "12": "I-ORGANISM",
47
+ "13": "B-EXP_ASSAY",
48
+ "14": "I-EXP_ASSAY",
49
+ "15": "B-DISEASE",
50
+ "16": "I-DISEASE",
51
+ "17": "B-CELL_LINE",
52
+ "18": "I-CELL_LINE"
53
+ },
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 3072,
56
+ "is_decoder": false,
57
+ "is_encoder_decoder": false,
58
+ "label2id": {
59
+ "B-CELL_LINE": 17,
60
+ "B-CELL_TYPE": 7,
61
+ "B-DISEASE": 15,
62
+ "B-EXP_ASSAY": 13,
63
+ "B-GENEPROD": 3,
64
+ "B-ORGANISM": 11,
65
+ "B-SMALL_MOLECULE": 1,
66
+ "B-SUBCELLULAR": 5,
67
+ "B-TISSUE": 9,
68
+ "I-CELL_LINE": 18,
69
+ "I-CELL_TYPE": 8,
70
+ "I-DISEASE": 16,
71
+ "I-EXP_ASSAY": 14,
72
+ "I-GENEPROD": 4,
73
+ "I-ORGANISM": 12,
74
+ "I-SMALL_MOLECULE": 2,
75
+ "I-SUBCELLULAR": 6,
76
+ "I-TISSUE": 10,
77
+ "O": 0
78
+ },
79
+ "layer_norm_eps": 1e-12,
80
+ "length_penalty": 1.0,
81
+ "max_length": 20,
82
+ "max_position_embeddings": 512,
83
+ "min_length": 0,
84
+ "model_type": "bert",
85
+ "no_repeat_ngram_size": 0,
86
+ "num_attention_heads": 12,
87
+ "num_beam_groups": 1,
88
+ "num_beams": 1,
89
+ "num_hidden_layers": 12,
90
+ "num_return_sequences": 1,
91
+ "output_attentions": false,
92
+ "output_hidden_states": false,
93
+ "output_scores": false,
94
+ "pad_token_id": 0,
95
+ "position_embedding_type": "absolute",
96
+ "prefix": null,
97
+ "problem_type": null,
98
+ "pruned_heads": {},
99
+ "remove_invalid_values": false,
100
+ "repetition_penalty": 1.0,
101
+ "return_dict": true,
102
+ "return_dict_in_generate": false,
103
+ "sep_token_id": null,
104
+ "suppress_tokens": null,
105
+ "task_specific_params": null,
106
+ "temperature": 1.0,
107
+ "tf_legacy_loss": false,
108
+ "tie_encoder_decoder": false,
109
+ "tie_word_embeddings": true,
110
+ "tokenizer_class": null,
111
+ "top_k": 50,
112
+ "top_p": 1.0,
113
+ "torch_dtype": null,
114
+ "torchscript": false,
115
+ "transformers_version": "4.33.0",
116
+ "type_vocab_size": 2,
117
+ "typical_p": 1.0,
118
+ "use_bfloat16": false,
119
+ "use_cache": true,
120
+ "vocab_size": 30524
121
+ },
122
+ "entity_max_length": 8,
123
+ "id2label": {
124
+ "0": "O",
125
+ "1": "CELL_LINE",
126
+ "2": "CELL_TYPE",
127
+ "3": "DISEASE",
128
+ "4": "EXP_ASSAY",
129
+ "5": "GENEPROD",
130
+ "6": "ORGANISM",
131
+ "7": "SMALL_MOLECULE",
132
+ "8": "SUBCELLULAR",
133
+ "9": "TISSUE"
134
+ },
135
+ "id2reduced_id": {
136
+ "0": 0,
137
+ "1": 7,
138
+ "2": 7,
139
+ "3": 5,
140
+ "4": 5,
141
+ "5": 8,
142
+ "6": 8,
143
+ "7": 2,
144
+ "8": 2,
145
+ "9": 9,
146
+ "10": 9,
147
+ "11": 6,
148
+ "12": 6,
149
+ "13": 4,
150
+ "14": 4,
151
+ "15": 3,
152
+ "16": 3,
153
+ "17": 1,
154
+ "18": 1
155
+ },
156
+ "label2id": {
157
+ "CELL_LINE": 1,
158
+ "CELL_TYPE": 2,
159
+ "DISEASE": 3,
160
+ "EXP_ASSAY": 4,
161
+ "GENEPROD": 5,
162
+ "O": 0,
163
+ "ORGANISM": 6,
164
+ "SMALL_MOLECULE": 7,
165
+ "SUBCELLULAR": 8,
166
+ "TISSUE": 9
167
+ },
168
+ "marker_max_length": 128,
169
+ "max_next_context": null,
170
+ "max_prev_context": null,
171
+ "model_max_length": 256,
172
+ "model_max_length_default": 512,
173
+ "model_type": "span-marker",
174
+ "span_marker_version": "1.3.1.dev",
175
+ "torch_dtype": "float32",
176
+ "trained_with_document_context": false,
177
+ "transformers_version": "4.33.0",
178
+ "vocab_size": 30524
179
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d1e3e40aa72cffd3f6fd38bb23a67b54ccdfda67e781ce4b717b111934267b
3
+ size 438062705
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff