Hugging Face's logo

PuxAI
/
GenPII-framework

Safetensors
Model card Files
xet
 Community
PuxAI commited on
Commit
287f391
·
verified ·
1 Parent(s): 9869417

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/gliner_config.json +105 -0
  2. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/optimizer.pt +3 -0
  3. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/pytorch_model.bin +3 -0
  4. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/rng_state.pth +3 -0
  5. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/scheduler.pt +3 -0
  6. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/tokenizer.json +0 -0
  7. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/tokenizer_config.json +24 -0
  8. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/trainer_state.json +33 -0
  9. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/gliner_config.json +105 -0
  10. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/pytorch_model.bin +3 -0
  11. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/tokenizer.json +0 -0
  12. ai4privacy_500k/GLiNER-NVIDIA-Finetuned/tokenizer_config.json +24 -0
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/gliner_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "dtype": null,
16
+ "eos_token_id": null,
17
+ "finetuning_task": null,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "layer_norm_eps": 1e-07,
34
+ "legacy": true,
35
+ "max_position_embeddings": 512,
36
+ "max_relative_positions": -1,
37
+ "model_type": "deberta-v2",
38
+ "norm_rel_ebd": "layer_norm",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 1024,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "relative_attention": true,
57
+ "return_dict": true,
58
+ "sep_token_id": null,
59
+ "share_att_key": true,
60
+ "task_specific_params": null,
61
+ "tf_legacy_loss": false,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "torchscript": false,
66
+ "type_vocab_size": 0,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 128004
69
+ },
70
+ "ent_token": "<<ENT>>",
71
+ "eos_token_id": 2,
72
+ "eval_every": 5000,
73
+ "fine_tune": true,
74
+ "fuse_layers": false,
75
+ "has_rnn": true,
76
+ "hidden_size": 512,
77
+ "labels_encoder": null,
78
+ "labels_encoder_config": null,
79
+ "lr_encoder": "1e-5",
80
+ "lr_others": "5e-5",
81
+ "max_len": 384,
82
+ "max_neg_type_ratio": 1,
83
+ "max_types": 25,
84
+ "max_width": 12,
85
+ "model_name": "microsoft/deberta-v3-large",
86
+ "model_type": null,
87
+ "name": "correct",
88
+ "num_post_fusion_layers": 1,
89
+ "num_rnn_layers": 1,
90
+ "num_steps": 30000,
91
+ "pad_token_id": 0,
92
+ "post_fusion_schema": "",
93
+ "random_drop": true,
94
+ "sep_token": "<<SEP>>",
95
+ "shuffle_types": true,
96
+ "size_sup": -1,
97
+ "span_mode": "markerV0",
98
+ "subtoken_pooling": "first",
99
+ "train_batch_size": 8,
100
+ "transformers_version": "5.3.0",
101
+ "use_cache": false,
102
+ "vocab_size": 128004,
103
+ "warmup_ratio": 3000,
104
+ "words_splitter_type": "whitespace"
105
+ }
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95160d2070a1730f206cc65410042a7a4495f7c3dba2d5c0fa679181dd51fad6
3
+ size 2873
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:105de9df0bb4e6596a2ad452371322a650ad89a6fda90ec001014ce2f1f0440e
3
+ size 14645
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26862b1dbdfd4b405c54507d09756536d20cf856229f9b6bc9ae65f91add93fd
3
+ size 1529
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "clean_up_tokenization_spaces": false,
6
+ "cls_token": "[CLS]",
7
+ "do_lower_case": false,
8
+ "eos_token": "[SEP]",
9
+ "is_local": true,
10
+ "mask_token": "[MASK]",
11
+ "max_length": null,
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "[PAD]",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/checkpoint-32/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 32,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 500,
13
+ "max_steps": 32,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 1,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 0.0,
30
+ "train_batch_size": 16,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/gliner_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "dtype": null,
16
+ "eos_token_id": null,
17
+ "finetuning_task": null,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "layer_norm_eps": 1e-07,
34
+ "legacy": true,
35
+ "max_position_embeddings": 512,
36
+ "max_relative_positions": -1,
37
+ "model_type": "deberta-v2",
38
+ "norm_rel_ebd": "layer_norm",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 0,
44
+ "pooler_dropout": 0,
45
+ "pooler_hidden_act": "gelu",
46
+ "pooler_hidden_size": 1024,
47
+ "pos_att_type": [
48
+ "p2c",
49
+ "c2p"
50
+ ],
51
+ "position_biased_input": false,
52
+ "position_buckets": 256,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "relative_attention": true,
57
+ "return_dict": true,
58
+ "sep_token_id": null,
59
+ "share_att_key": true,
60
+ "task_specific_params": null,
61
+ "tf_legacy_loss": false,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "torchscript": false,
66
+ "type_vocab_size": 0,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 128004
69
+ },
70
+ "ent_token": "<<ENT>>",
71
+ "eos_token_id": 2,
72
+ "eval_every": 5000,
73
+ "fine_tune": true,
74
+ "fuse_layers": false,
75
+ "has_rnn": true,
76
+ "hidden_size": 512,
77
+ "labels_encoder": null,
78
+ "labels_encoder_config": null,
79
+ "lr_encoder": "1e-5",
80
+ "lr_others": "5e-5",
81
+ "max_len": 384,
82
+ "max_neg_type_ratio": 1,
83
+ "max_types": 25,
84
+ "max_width": 12,
85
+ "model_name": "microsoft/deberta-v3-large",
86
+ "model_type": null,
87
+ "name": "correct",
88
+ "num_post_fusion_layers": 1,
89
+ "num_rnn_layers": 1,
90
+ "num_steps": 30000,
91
+ "pad_token_id": 0,
92
+ "post_fusion_schema": "",
93
+ "random_drop": true,
94
+ "sep_token": "<<SEP>>",
95
+ "shuffle_types": true,
96
+ "size_sup": -1,
97
+ "span_mode": "markerV0",
98
+ "subtoken_pooling": "first",
99
+ "train_batch_size": 8,
100
+ "transformers_version": "5.3.0",
101
+ "use_cache": false,
102
+ "vocab_size": 128004,
103
+ "warmup_ratio": 3000,
104
+ "words_splitter_type": "whitespace"
105
+ }
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abe4edc77f96f88e966f61f2c72b785f8d6f1d5aca2bd845e7ac15dac597a5d
3
+ size 1782005383
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ai4privacy_500k/GLiNER-NVIDIA-Finetuned/tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "clean_up_tokenization_spaces": false,
6
+ "cls_token": "[CLS]",
7
+ "do_lower_case": false,
8
+ "eos_token": "[SEP]",
9
+ "is_local": true,
10
+ "mask_token": "[MASK]",
11
+ "max_length": null,
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "[PAD]",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }