Token Classification
GLiNER
PyTorch
ONNX
English
MikeG27 commited on
Commit
614a902
·
verified ·
1 Parent(s): c172906

Upload folder using huggingface_hub

Browse files
gliner_config.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class_token_index": 128002,
3
+ "dropout": 0.4,
4
+ "embed_ent_token": true,
5
+ "encoder_config": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "microsoft/deberta-v3-small",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "cross_attention_hidden_size": null,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": null,
22
+ "exponential_decay_length_penalty": null,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "is_decoder": false,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-07,
42
+ "legacy": true,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "max_relative_positions": -1,
47
+ "min_length": 0,
48
+ "model_type": "deberta-v2",
49
+ "no_repeat_ngram_size": 0,
50
+ "norm_rel_ebd": "layer_norm",
51
+ "num_attention_heads": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 6,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 0,
60
+ "pooler_dropout": 0,
61
+ "pooler_hidden_act": "gelu",
62
+ "pooler_hidden_size": 768,
63
+ "pos_att_type": [
64
+ "p2c",
65
+ "c2p"
66
+ ],
67
+ "position_biased_input": false,
68
+ "position_buckets": 256,
69
+ "prefix": null,
70
+ "problem_type": null,
71
+ "pruned_heads": {},
72
+ "relative_attention": true,
73
+ "remove_invalid_values": false,
74
+ "repetition_penalty": 1.0,
75
+ "return_dict": true,
76
+ "return_dict_in_generate": false,
77
+ "sep_token_id": null,
78
+ "share_att_key": true,
79
+ "suppress_tokens": null,
80
+ "task_specific_params": null,
81
+ "temperature": 1.0,
82
+ "tf_legacy_loss": false,
83
+ "tie_encoder_decoder": false,
84
+ "tie_word_embeddings": true,
85
+ "tokenizer_class": null,
86
+ "top_k": 50,
87
+ "top_p": 1.0,
88
+ "torch_dtype": null,
89
+ "torchscript": false,
90
+ "type_vocab_size": 0,
91
+ "typical_p": 1.0,
92
+ "use_bfloat16": false,
93
+ "vocab_size": 128004
94
+ },
95
+ "ent_token": "<<ENT>>",
96
+ "eval_every": 5000,
97
+ "fine_tune": true,
98
+ "fuse_layers": false,
99
+ "has_rnn": true,
100
+ "hidden_size": 512,
101
+ "id2label": {
102
+ "1": "api_key",
103
+ "2": "bank_routing_number",
104
+ "3": "bban",
105
+ "4": "company",
106
+ "5": "credit_card_number",
107
+ "6": "credit_card_security_code",
108
+ "7": "customer_id",
109
+ "8": "date",
110
+ "9": "date_of_birth",
111
+ "10": "date_time",
112
+ "11": "driver_license_number",
113
+ "12": "email",
114
+ "13": "employee_id",
115
+ "14": "first_name",
116
+ "15": "iban",
117
+ "16": "ipv4",
118
+ "17": "ipv6",
119
+ "18": "last_name",
120
+ "19": "local_latlng",
121
+ "20": "name",
122
+ "21": "passport_number",
123
+ "22": "password",
124
+ "23": "phone_number",
125
+ "24": "ssn",
126
+ "25": "street_address",
127
+ "26": "swift_bic_code",
128
+ "27": "time"
129
+ },
130
+ "label2id": {
131
+ "api_key": 1,
132
+ "bank_routing_number": 2,
133
+ "bban": 3,
134
+ "company": 4,
135
+ "credit_card_number": 5,
136
+ "credit_card_security_code": 6,
137
+ "customer_id": 7,
138
+ "date": 8,
139
+ "date_of_birth": 9,
140
+ "date_time": 10,
141
+ "driver_license_number": 11,
142
+ "email": 12,
143
+ "employee_id": 13,
144
+ "first_name": 14,
145
+ "iban": 15,
146
+ "ipv4": 16,
147
+ "ipv6": 17,
148
+ "last_name": 18,
149
+ "local_latlng": 19,
150
+ "name": 20,
151
+ "passport_number": 21,
152
+ "password": 22,
153
+ "phone_number": 23,
154
+ "ssn": 24,
155
+ "street_address": 25,
156
+ "swift_bic_code": 26,
157
+ "time": 27
158
+ },
159
+ "labels_encoder": null,
160
+ "labels_encoder_config": null,
161
+ "lr_encoder": "1e-5",
162
+ "lr_others": "5e-5",
163
+ "max_len": 384,
164
+ "max_neg_type_ratio": 1,
165
+ "max_types": 25,
166
+ "max_width": 12,
167
+ "model_name": "microsoft/deberta-v3-small",
168
+ "model_type": "gliner",
169
+ "name": "correct",
170
+ "num_post_fusion_layers": 1,
171
+ "num_steps": 30000,
172
+ "post_fusion_schema": "",
173
+ "random_drop": true,
174
+ "sep_token": "<<SEP>>",
175
+ "shuffle_types": true,
176
+ "size_sup": -1,
177
+ "span_mode": "markerV0",
178
+ "subtoken_pooling": "first",
179
+ "train_batch_size": 8,
180
+ "transformers_version": "4.48.3",
181
+ "vocab_size": 128004,
182
+ "warmup_ratio": 3000,
183
+ "words_splitter_type": "whitespace"
184
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e33b34280d1e85a6cbf044537d43d0ae38c7e9a449d4a467d25532ddfdc014c
3
+ size 611243898
model.quant.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73d9aaf0f667aa9b7d52fedd0259931d3bee025876ebe364a25d5730cb7a1f7
3
+ size 154767149
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5aa64961c7658b48559738b2bbf8e60826fceb1ce12a73902162c464d818674
3
+ size 610638254
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128001": {
44
+ "content": "[FLERT]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "128002": {
52
+ "content": "<<ENT>>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "128003": {
60
+ "content": "<<SEP>>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ }
67
+ },
68
+ "bos_token": "[CLS]",
69
+ "clean_up_tokenization_spaces": false,
70
+ "cls_token": "[CLS]",
71
+ "do_lower_case": false,
72
+ "eos_token": "[SEP]",
73
+ "extra_special_tokens": {},
74
+ "mask_token": "[MASK]",
75
+ "model_max_length": 1000000000000000019884624838656,
76
+ "pad_token": "[PAD]",
77
+ "sep_token": "[SEP]",
78
+ "sp_model_kwargs": {},
79
+ "split_by_punct": false,
80
+ "tokenizer_class": "DebertaV2Tokenizer",
81
+ "unk_token": "[UNK]",
82
+ "vocab_type": "spm"
83
+ }