Hugging Face's logo

arthrod
/
gliner-ettin-68m-ptbr-pii-full-3x-v1

Token Classification
GLiNER
Portuguese
English
ner
pii
portuguese
brazilian-portuguese
token-level
Model card Files
xet
 Community
arthrod commited on
Commit
0bc48ee
·
verified ·
1 Parent(s): 5c2b7af

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. checkpoint-55200/gliner_config.json +121 -0
  2. checkpoint-55200/optimizer.pt +3 -0
  3. checkpoint-55200/pytorch_model.bin +3 -0
  4. checkpoint-55200/rng_state.pth +3 -0
  5. checkpoint-55200/scheduler.pt +3 -0
  6. checkpoint-55200/tokenizer.json +0 -0
  7. checkpoint-55200/tokenizer_config.json +16 -0
  8. checkpoint-55200/trainer_state.json +0 -0
checkpoint-55200/gliner_config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class_token_index": 50369,
3
+ "dropout": 0.3,
4
+ "embed_ent_token": true,
5
+ "encoder_config": {
6
+ "_name_or_path": "jhu-clsp/ettin-encoder-68m",
7
+ "architectures": [
8
+ "ModernBertForMaskedLM"
9
+ ],
10
+ "attention_bias": false,
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 50281,
13
+ "causal_mask": false,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_activation": "gelu",
16
+ "classifier_bias": false,
17
+ "classifier_dropout": 0.0,
18
+ "classifier_pooling": "mean",
19
+ "cls_token_id": 50281,
20
+ "decoder_bias": true,
21
+ "deterministic_flash_attn": false,
22
+ "dtype": "float32",
23
+ "embedding_dropout": 0.0,
24
+ "eos_token_id": 50282,
25
+ "global_attn_every_n_layers": 3,
26
+ "gradient_checkpointing": false,
27
+ "hidden_activation": "gelu",
28
+ "hidden_size": 512,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_cutoff_factor": 2.0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 768,
36
+ "is_causal": false,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "layer_types": [
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "full_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "full_attention"
63
+ ],
64
+ "local_attention": 128,
65
+ "max_position_embeddings": 7999,
66
+ "mlp_bias": false,
67
+ "mlp_dropout": 0.0,
68
+ "model_type": "modernbert",
69
+ "norm_bias": false,
70
+ "norm_eps": 1e-05,
71
+ "num_attention_heads": 8,
72
+ "num_hidden_layers": 19,
73
+ "output_attentions": false,
74
+ "output_hidden_states": false,
75
+ "pad_token_id": 50283,
76
+ "position_embedding_type": "sans_pos",
77
+ "problem_type": null,
78
+ "return_dict": true,
79
+ "rope_parameters": {
80
+ "full_attention": {
81
+ "rope_theta": 160000.0,
82
+ "rope_type": "default"
83
+ },
84
+ "sliding_attention": {
85
+ "rope_theta": 160000.0,
86
+ "rope_type": "default"
87
+ }
88
+ },
89
+ "sep_token_id": 50282,
90
+ "sparse_pred_ignore_index": -100,
91
+ "sparse_prediction": false,
92
+ "tie_word_embeddings": true,
93
+ "vocab_size": 50371
94
+ },
95
+ "ent_token": "<<ENT>>",
96
+ "fine_tune": true,
97
+ "fuse_layers": false,
98
+ "hidden_size": 512,
99
+ "max_len": 1024,
100
+ "max_neg_type_ratio": 1,
101
+ "max_types": 100,
102
+ "max_width": 100,
103
+ "model_name": "jhu-clsp/ettin-encoder-68m",
104
+ "model_type": null,
105
+ "name": "gliner-ettin-68m-ptbr-pii-full-3x",
106
+ "neg_spans_ratio": 1.0,
107
+ "num_post_fusion_layers": 1,
108
+ "num_rnn_layers": 1,
109
+ "pad_token_id": 50283,
110
+ "post_fusion_schema": null,
111
+ "represent_spans": false,
112
+ "sep_token": "<<SEP>>",
113
+ "span_loss_coef": 1.0,
114
+ "span_mode": "token_level",
115
+ "subtoken_pooling": "first",
116
+ "token_loss_coef": 1.0,
117
+ "transformers_version": "5.1.0",
118
+ "use_cache": false,
119
+ "vocab_size": 50371,
120
+ "words_splitter_type": "whitespace"
121
+ }
checkpoint-55200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b03438b20e8359a88cfc97fcf1344a69287d0c6aa520ff4b4bc4ef4f315e5a9
3
+ size 591533323
checkpoint-55200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b32dc0c32f02b9e2e874b378b4e853a494957dc8b44ec871814bb2730216c590
3
+ size 295757555
checkpoint-55200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f7e13ab4803b9686d7f743fd64ef1d8f10d92273c075401c14677333e6cda0
3
+ size 14645
checkpoint-55200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba9b83489d13e205318428dedbb0da1a5e4707e9d30914c91abedf4aca308c7
3
+ size 1529
checkpoint-55200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-55200/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_input_names": [
8
+ "input_ids",
9
+ "attention_mask"
10
+ ],
11
+ "model_max_length": 8192,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "[UNK]"
16
+ }
checkpoint-55200/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff