Hugging Face's logo

Mit1208
/
gliner-fine-tuned-pii-finance-multilingual

PyTorch
English
Model card Files Community
Mit1208 commited on
Commit
f02f018
•
1 Parent(s): 55f1b77

Push model using huggingface_hub.

Browse files
Files changed (7) hide show
  1. added_tokens.json +6 -0
  2. gliner_config.json +122 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +51 -0
  5. spm.model +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +86 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<<ENT>>": 128002,
3
+ "<<SEP>>": 128003,
4
+ "[FLERT]": 128001,
5
+ "[MASK]": 128000
6
+ }
gliner_config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class_token_index": 128002,
3
+ "dropout": 0.4,
4
+ "encoder_config": {
5
+ "_name_or_path": "microsoft/deberta-v3-small",
6
+ "add_cross_attention": false,
7
+ "architectures": null,
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "bad_words_ids": null,
10
+ "begin_suppress_tokens": null,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "diversity_penalty": 0.0,
16
+ "do_sample": false,
17
+ "early_stopping": false,
18
+ "encoder_no_repeat_ngram_size": 0,
19
+ "eos_token_id": null,
20
+ "exponential_decay_length_penalty": null,
21
+ "finetuning_task": null,
22
+ "forced_bos_token_id": null,
23
+ "forced_eos_token_id": null,
24
+ "hidden_act": "gelu",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 768,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "is_decoder": false,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "layer_norm_eps": 1e-07,
40
+ "length_penalty": 1.0,
41
+ "max_length": 20,
42
+ "max_position_embeddings": 512,
43
+ "max_relative_positions": -1,
44
+ "min_length": 0,
45
+ "model_type": "deberta-v2",
46
+ "no_repeat_ngram_size": 0,
47
+ "norm_rel_ebd": "layer_norm",
48
+ "num_attention_heads": 12,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 6,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 0,
57
+ "pooler_dropout": 0,
58
+ "pooler_hidden_act": "gelu",
59
+ "pooler_hidden_size": 768,
60
+ "pos_att_type": [
61
+ "p2c",
62
+ "c2p"
63
+ ],
64
+ "position_biased_input": false,
65
+ "position_buckets": 256,
66
+ "prefix": null,
67
+ "problem_type": null,
68
+ "pruned_heads": {},
69
+ "relative_attention": true,
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "sep_token_id": null,
75
+ "share_att_key": true,
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
+ "type_vocab_size": 0,
88
+ "typical_p": 1.0,
89
+ "use_bfloat16": false,
90
+ "vocab_size": 128004
91
+ },
92
+ "ent_token": "<<ENT>>",
93
+ "eval_every": 5000,
94
+ "fine_tune": true,
95
+ "fuse_layers": false,
96
+ "has_rnn": true,
97
+ "hidden_size": 512,
98
+ "labels_encoder": null,
99
+ "labels_encoder_config": null,
100
+ "lr_encoder": "1e-5",
101
+ "lr_others": "5e-5",
102
+ "max_len": 384,
103
+ "max_neg_type_ratio": 1,
104
+ "max_types": 25,
105
+ "max_width": 12,
106
+ "model_name": "microsoft/deberta-v3-small",
107
+ "model_type": "gliner",
108
+ "name": "correct",
109
+ "num_steps": 30000,
110
+ "post_fusion_schema": "",
111
+ "random_drop": true,
112
+ "sep_token": "<<SEP>>",
113
+ "shuffle_types": true,
114
+ "size_sup": -1,
115
+ "span_mode": "markerV0",
116
+ "subtoken_pooling": "first",
117
+ "train_batch_size": 8,
118
+ "transformers_version": "4.42.4",
119
+ "vocab_size": 128004,
120
+ "warmup_ratio": 3000,
121
+ "words_splitter_type": "whitespace"
122
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37930c693dcac7d6e7c1aebd30d4c7940d177b4240a2b5e74e8823153e1922e
3
+ size 610639626
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
70
+ "cls_token": "[CLS]",
71
+ "do_lower_case": false,
72
+ "eos_token": "[SEP]",
73
+ "mask_token": "[MASK]",
74
+ "max_length": null,
75
+ "model_max_length": 1000000000000000019884624838656,
76
+ "pad_to_multiple_of": null,
77
+ "pad_token": "[PAD]",
78
+ "pad_token_type_id": 0,
79
+ "padding_side": "right",
80
+ "sep_token": "[SEP]",
81
+ "sp_model_kwargs": {},
82
+ "split_by_punct": false,
83
+ "tokenizer_class": "DebertaV2Tokenizer",
84
+ "unk_token": "[UNK]",
85
+ "vocab_type": "spm"
86
+ }