jg-enosh commited on
Commit
4745966
·
verified ·
1 Parent(s): a59f6bc

Push model using huggingface_hub.

Browse files
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 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class_token_index": 128002,
3
+ "decoder_mode": null,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_attn_implementation_autoset": true,
8
+ "_name_or_path": "microsoft/deberta-v3-small",
9
+ "add_cross_attention": false,
10
+ "architectures": null,
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": false,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-07,
43
+ "legacy": true,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 512,
47
+ "max_relative_positions": -1,
48
+ "min_length": 0,
49
+ "model_type": "deberta-v2",
50
+ "no_repeat_ngram_size": 0,
51
+ "norm_rel_ebd": "layer_norm",
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 6,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 0,
61
+ "pooler_dropout": 0,
62
+ "pooler_hidden_act": "gelu",
63
+ "pooler_hidden_size": 768,
64
+ "pos_att_type": [
65
+ "p2c",
66
+ "c2p"
67
+ ],
68
+ "position_biased_input": false,
69
+ "position_buckets": 256,
70
+ "prefix": null,
71
+ "problem_type": null,
72
+ "pruned_heads": {},
73
+ "relative_attention": true,
74
+ "remove_invalid_values": false,
75
+ "repetition_penalty": 1.0,
76
+ "return_dict": true,
77
+ "return_dict_in_generate": false,
78
+ "sep_token_id": null,
79
+ "share_att_key": true,
80
+ "suppress_tokens": null,
81
+ "task_specific_params": null,
82
+ "temperature": 1.0,
83
+ "tf_legacy_loss": false,
84
+ "tie_encoder_decoder": false,
85
+ "tie_word_embeddings": true,
86
+ "tokenizer_class": null,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "torch_dtype": null,
90
+ "torchscript": false,
91
+ "type_vocab_size": 0,
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "vocab_size": 128004
95
+ },
96
+ "ent_token": "<<ENT>>",
97
+ "eval_every": 5000,
98
+ "fine_tune": true,
99
+ "full_decoder_context": true,
100
+ "fuse_layers": false,
101
+ "has_rnn": true,
102
+ "hidden_size": 512,
103
+ "labels_decoder": null,
104
+ "labels_decoder_config": null,
105
+ "labels_encoder": null,
106
+ "labels_encoder_config": null,
107
+ "lr_encoder": "1e-5",
108
+ "lr_others": "5e-5",
109
+ "max_len": 384,
110
+ "max_neg_type_ratio": 1,
111
+ "max_types": 25,
112
+ "max_width": 12,
113
+ "model_name": "microsoft/deberta-v3-small",
114
+ "model_type": "gliner",
115
+ "name": "correct",
116
+ "num_post_fusion_layers": 1,
117
+ "num_steps": 30000,
118
+ "post_fusion_schema": "",
119
+ "random_drop": true,
120
+ "sep_token": "<<SEP>>",
121
+ "shuffle_types": true,
122
+ "size_sup": -1,
123
+ "span_mode": "markerV0",
124
+ "subtoken_pooling": "first",
125
+ "train_batch_size": 8,
126
+ "transformers_version": "4.51.0",
127
+ "vocab_size": 128004,
128
+ "warmup_ratio": 3000,
129
+ "words_splitter_type": "whitespace"
130
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f53191fe91e60fefa410630f217b95a8903b18e7a14290796ac75d84a13b21
3
+ size 610640455
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
+ }
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 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }