tomaarsen HF staff commited on
Commit
35f487a
1 Parent(s): 1e3077f

Upload model

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: apache-2.0
4
+ library_name: span-marker
5
+ tags:
6
+ - span-marker
7
+ - token-classification
8
+ - ner
9
+ - named-entity-recognition
10
+ pipeline_tag: token-classification
11
+ ---
12
+
13
+ # SpanMarker for Named Entity Recognition
14
+
15
+ This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for Named Entity Recognition. In particular, this SpanMarker model uses [bert-base-cased](https://huggingface.co/bert-base-cased) as the underlying encoder.
16
+
17
+
18
+ ## Usage
19
+
20
+ To use this model for inference, first install the `span_marker` library:
21
+
22
+ ```bash
23
+ pip install span_marker
24
+ ```
25
+
26
+ You can then run inference with this model like so:
27
+
28
+ ```python
29
+ from span_marker import SpanMarkerModel
30
+
31
+ # Download from the 🤗 Hub
32
+ model = SpanMarkerModel.from_pretrained("span_marker_model_name")
33
+ # Run inference
34
+ entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
35
+ ```
36
+
37
+ See the [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) repository for documentation and additional information on this library.
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<end>": 28997,
3
+ "<start>": 28996
4
+ }
config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models\\span_marker_bert_base_acronyms\\checkpoint-final",
3
+ "architectures": [
4
+ "SpanMarkerModel"
5
+ ],
6
+ "encoder": {
7
+ "_name_or_path": "bert-base-cased",
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": "B-long",
35
+ "1": "B-short",
36
+ "2": "I-long",
37
+ "3": "I-short",
38
+ "4": "O"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
42
+ "is_decoder": false,
43
+ "is_encoder_decoder": false,
44
+ "label2id": {
45
+ "B-long": 0,
46
+ "B-short": 1,
47
+ "I-long": 2,
48
+ "I-short": 3,
49
+ "O": 4
50
+ },
51
+ "layer_norm_eps": 1e-12,
52
+ "length_penalty": 1.0,
53
+ "max_length": 20,
54
+ "max_position_embeddings": 512,
55
+ "min_length": 0,
56
+ "model_type": "bert",
57
+ "no_repeat_ngram_size": 0,
58
+ "num_attention_heads": 12,
59
+ "num_beam_groups": 1,
60
+ "num_beams": 1,
61
+ "num_hidden_layers": 12,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 0,
67
+ "position_embedding_type": "absolute",
68
+ "prefix": null,
69
+ "problem_type": null,
70
+ "pruned_heads": {},
71
+ "remove_invalid_values": false,
72
+ "repetition_penalty": 1.0,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
75
+ "sep_token_id": null,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": null,
78
+ "temperature": 1.0,
79
+ "tf_legacy_loss": false,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": true,
82
+ "tokenizer_class": null,
83
+ "top_k": 50,
84
+ "top_p": 1.0,
85
+ "torch_dtype": null,
86
+ "torchscript": false,
87
+ "transformers_version": "4.31.0",
88
+ "type_vocab_size": 2,
89
+ "typical_p": 1.0,
90
+ "use_bfloat16": false,
91
+ "use_cache": true,
92
+ "vocab_size": 28998
93
+ },
94
+ "entity_max_length": 8,
95
+ "id2label": {
96
+ "0": "O",
97
+ "1": "LONG",
98
+ "2": "SHORT"
99
+ },
100
+ "id2reduced_id": {
101
+ "0": 1,
102
+ "1": 2,
103
+ "2": 1,
104
+ "3": 2,
105
+ "4": 0
106
+ },
107
+ "label2id": {
108
+ "LONG": 1,
109
+ "O": 0,
110
+ "SHORT": 2
111
+ },
112
+ "marker_max_length": 128,
113
+ "max_next_context": null,
114
+ "max_prev_context": null,
115
+ "model_max_length": 256,
116
+ "model_max_length_default": 512,
117
+ "model_type": "span-marker",
118
+ "span_marker_version": "1.2.5.dev",
119
+ "torch_dtype": "float32",
120
+ "trained_with_document_context": false,
121
+ "transformers_version": "4.31.0",
122
+ "vocab_size": 28998
123
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b60063b813ab8a8a15e8c15c7258685cd21fe2ca6a5e0e3d2f347140b33f747e
3
+ size 433331825
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": false,
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