Hugging Face's logo

PuxAI
/
GenPII-framework-Data

Safetensors
Model card Files
xet
 Community
PuxAI commited on
Commit
88d0816
·
verified ·
1 Parent(s): e376e44

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/config.json +66 -22
  2. open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/model.safetensors +2 -2
  3. open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/optimizer.pt +2 -2
  4. open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/rng_state.pth +1 -1
  5. open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/tokenizer.json +0 -0
  6. open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/tokenizer_config.json +7 -5
  7. open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/trainer_state.json +5 -5
  8. open-pii-masking-500k-ai4privacy/TokenBased-CRF/config.json +66 -22
  9. open-pii-masking-500k-ai4privacy/TokenBased-CRF/pytorch_model.bin +2 -2
  10. open-pii-masking-500k-ai4privacy/TokenBased-CRF/tokenizer.json +0 -0
  11. open-pii-masking-500k-ai4privacy/TokenBased-CRF/tokenizer_config.json +7 -5
open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/config.json CHANGED
@@ -1,16 +1,23 @@
1
  {
2
- "add_cross_attention": false,
3
  "architectures": [
4
  "TransformerCrfForTokenClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": null,
8
- "classifier_dropout": null,
9
- "directionality": "bidi",
 
 
 
 
 
 
10
  "dtype": "float32",
11
- "eos_token_id": null,
12
- "hidden_act": "gelu",
13
- "hidden_dropout_prob": 0.1,
 
 
14
  "hidden_size": 768,
15
  "id2label": {
16
  "0": "O",
@@ -55,9 +62,9 @@
55
  "39": "B-ZIPCODE",
56
  "40": "I-ZIPCODE"
57
  },
 
58
  "initializer_range": 0.02,
59
- "intermediate_size": 3072,
60
- "is_decoder": false,
61
  "label2id": {
62
  "B-AGE": 1,
63
  "B-BUILDINGNUM": 3,
@@ -101,20 +108,57 @@
101
  "I-ZIPCODE": 40,
102
  "O": 0
103
  },
104
- "layer_norm_eps": 1e-12,
105
- "max_position_embeddings": 512,
106
- "model_type": "bert",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  "num_attention_heads": 12,
108
- "num_hidden_layers": 12,
109
- "pad_token_id": 0,
110
- "pooler_fc_size": 768,
111
- "pooler_num_attention_heads": 12,
112
- "pooler_num_fc_layers": 3,
113
- "pooler_size_per_head": 128,
114
- "pooler_type": "first_token_transform",
 
 
 
 
 
 
 
 
 
115
  "tie_word_embeddings": true,
116
  "transformers_version": "5.3.0",
117
- "type_vocab_size": 2,
118
  "use_cache": false,
119
- "vocab_size": 119547
120
  }
 
1
  {
 
2
  "architectures": [
3
  "TransformerCrfForTokenClassification"
4
  ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
  "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
  "hidden_size": 768,
22
  "id2label": {
23
  "0": "O",
 
62
  "39": "B-ZIPCODE",
63
  "40": "I-ZIPCODE"
64
  },
65
+ "initializer_cutoff_factor": 2.0,
66
  "initializer_range": 0.02,
67
+ "intermediate_size": 1152,
 
68
  "label2id": {
69
  "B-AGE": 1,
70
  "B-BUILDINGNUM": 3,
 
108
  "I-ZIPCODE": 40,
109
  "O": 0
110
  },
111
+ "layer_norm_eps": 1e-05,
112
+ "layer_types": [
113
+ "full_attention",
114
+ "sliding_attention",
115
+ "sliding_attention",
116
+ "full_attention",
117
+ "sliding_attention",
118
+ "sliding_attention",
119
+ "full_attention",
120
+ "sliding_attention",
121
+ "sliding_attention",
122
+ "full_attention",
123
+ "sliding_attention",
124
+ "sliding_attention",
125
+ "full_attention",
126
+ "sliding_attention",
127
+ "sliding_attention",
128
+ "full_attention",
129
+ "sliding_attention",
130
+ "sliding_attention",
131
+ "full_attention",
132
+ "sliding_attention",
133
+ "sliding_attention",
134
+ "full_attention"
135
+ ],
136
+ "local_attention": 128,
137
+ "max_position_embeddings": 8192,
138
+ "mlp_bias": false,
139
+ "mlp_dropout": 0.0,
140
+ "model_type": "modernbert",
141
+ "norm_bias": false,
142
+ "norm_eps": 1e-05,
143
  "num_attention_heads": 12,
144
+ "num_hidden_layers": 22,
145
+ "pad_token_id": 50283,
146
+ "position_embedding_type": "absolute",
147
+ "rope_parameters": {
148
+ "full_attention": {
149
+ "rope_theta": 160000.0,
150
+ "rope_type": "default"
151
+ },
152
+ "sliding_attention": {
153
+ "rope_theta": 10000.0,
154
+ "rope_type": "default"
155
+ }
156
+ },
157
+ "sep_token_id": 50282,
158
+ "sparse_pred_ignore_index": -100,
159
+ "sparse_prediction": false,
160
  "tie_word_embeddings": true,
161
  "transformers_version": "5.3.0",
 
162
  "use_cache": false,
163
+ "vocab_size": 50368
164
  }
open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:988fe44477a3633c01f74398d42a45d67e46e272c89bf183fa404ff371ae3be6
3
- size 711572104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14174801d86131d4e9aa1e0d6df08bdee9da59d4f0229589f19f0fc8c665319
3
+ size 596205320
open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ce6f82e3963c0b944789c4de89f4bc3affccf18537a788f4d88f11ad232af03
3
- size 1418541131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf89658473422e1c0214f65abe3aa73b5dbb589a8625dfca0af4d182e4eb0459
3
+ size 1192499723
open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f39eab8ed980549bfffcd8b948e8852bef979d820a1c47a898b2c9f270cc3986
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08504cb4efee454165d24aa00ad8e58713d98093f38b30f8a5112618d186bfa1
3
  size 14645
open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/tokenizer_config.json CHANGED
@@ -1,15 +1,17 @@
1
  {
2
  "add_prefix_space": true,
3
  "backend": "tokenizers",
 
4
  "cls_token": "[CLS]",
5
- "do_lower_case": false,
6
  "is_local": false,
7
  "mask_token": "[MASK]",
8
- "model_max_length": 512,
 
 
 
 
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
  "unk_token": "[UNK]"
15
  }
 
1
  {
2
  "add_prefix_space": true,
3
  "backend": "tokenizers",
4
+ "clean_up_tokenization_spaces": true,
5
  "cls_token": "[CLS]",
 
6
  "is_local": false,
7
  "mask_token": "[MASK]",
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
  "pad_token": "[PAD]",
14
  "sep_token": "[SEP]",
15
+ "tokenizer_class": "TokenizersBackend",
 
 
16
  "unk_token": "[UNK]"
17
  }
open-pii-masking-500k-ai4privacy/TokenBased-CRF/checkpoint-63/trainer_state.json CHANGED
@@ -11,10 +11,10 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_loss": 24.712289810180664,
15
- "eval_runtime": 1.6052,
16
- "eval_samples_per_second": 62.296,
17
- "eval_steps_per_second": 8.098,
18
  "step": 63
19
  }
20
  ],
@@ -35,7 +35,7 @@
35
  "attributes": {}
36
  }
37
  },
38
- "total_flos": 131604301824000.0,
39
  "train_batch_size": 8,
40
  "trial_name": null,
41
  "trial_params": null
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "eval_loss": 39.32425308227539,
15
+ "eval_runtime": 1.7874,
16
+ "eval_samples_per_second": 55.947,
17
+ "eval_steps_per_second": 7.273,
18
  "step": 63
19
  }
20
  ],
 
35
  "attributes": {}
36
  }
37
  },
38
+ "total_flos": 169520547840000.0,
39
  "train_batch_size": 8,
40
  "trial_name": null,
41
  "trial_params": null
open-pii-masking-500k-ai4privacy/TokenBased-CRF/config.json CHANGED
@@ -1,16 +1,23 @@
1
  {
2
- "add_cross_attention": false,
3
  "architectures": [
4
  "TransformerCrfForTokenClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": null,
8
- "classifier_dropout": null,
9
- "directionality": "bidi",
 
 
 
 
 
 
10
  "dtype": "float32",
11
- "eos_token_id": null,
12
- "hidden_act": "gelu",
13
- "hidden_dropout_prob": 0.1,
 
 
14
  "hidden_size": 768,
15
  "id2label": {
16
  "0": "O",
@@ -55,9 +62,9 @@
55
  "39": "B-ZIPCODE",
56
  "40": "I-ZIPCODE"
57
  },
 
58
  "initializer_range": 0.02,
59
- "intermediate_size": 3072,
60
- "is_decoder": false,
61
  "label2id": {
62
  "B-AGE": 1,
63
  "B-BUILDINGNUM": 3,
@@ -101,20 +108,57 @@
101
  "I-ZIPCODE": 40,
102
  "O": 0
103
  },
104
- "layer_norm_eps": 1e-12,
105
- "max_position_embeddings": 512,
106
- "model_type": "bert",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  "num_attention_heads": 12,
108
- "num_hidden_layers": 12,
109
- "pad_token_id": 0,
110
- "pooler_fc_size": 768,
111
- "pooler_num_attention_heads": 12,
112
- "pooler_num_fc_layers": 3,
113
- "pooler_size_per_head": 128,
114
- "pooler_type": "first_token_transform",
 
 
 
 
 
 
 
 
 
115
  "tie_word_embeddings": true,
116
  "transformers_version": "5.3.0",
117
- "type_vocab_size": 2,
118
  "use_cache": false,
119
- "vocab_size": 119547
120
  }
 
1
  {
 
2
  "architectures": [
3
  "TransformerCrfForTokenClassification"
4
  ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
  "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
  "hidden_size": 768,
22
  "id2label": {
23
  "0": "O",
 
62
  "39": "B-ZIPCODE",
63
  "40": "I-ZIPCODE"
64
  },
65
+ "initializer_cutoff_factor": 2.0,
66
  "initializer_range": 0.02,
67
+ "intermediate_size": 1152,
 
68
  "label2id": {
69
  "B-AGE": 1,
70
  "B-BUILDINGNUM": 3,
 
108
  "I-ZIPCODE": 40,
109
  "O": 0
110
  },
111
+ "layer_norm_eps": 1e-05,
112
+ "layer_types": [
113
+ "full_attention",
114
+ "sliding_attention",
115
+ "sliding_attention",
116
+ "full_attention",
117
+ "sliding_attention",
118
+ "sliding_attention",
119
+ "full_attention",
120
+ "sliding_attention",
121
+ "sliding_attention",
122
+ "full_attention",
123
+ "sliding_attention",
124
+ "sliding_attention",
125
+ "full_attention",
126
+ "sliding_attention",
127
+ "sliding_attention",
128
+ "full_attention",
129
+ "sliding_attention",
130
+ "sliding_attention",
131
+ "full_attention",
132
+ "sliding_attention",
133
+ "sliding_attention",
134
+ "full_attention"
135
+ ],
136
+ "local_attention": 128,
137
+ "max_position_embeddings": 8192,
138
+ "mlp_bias": false,
139
+ "mlp_dropout": 0.0,
140
+ "model_type": "modernbert",
141
+ "norm_bias": false,
142
+ "norm_eps": 1e-05,
143
  "num_attention_heads": 12,
144
+ "num_hidden_layers": 22,
145
+ "pad_token_id": 50283,
146
+ "position_embedding_type": "absolute",
147
+ "rope_parameters": {
148
+ "full_attention": {
149
+ "rope_theta": 160000.0,
150
+ "rope_type": "default"
151
+ },
152
+ "sliding_attention": {
153
+ "rope_theta": 10000.0,
154
+ "rope_type": "default"
155
+ }
156
+ },
157
+ "sep_token_id": 50282,
158
+ "sparse_pred_ignore_index": -100,
159
+ "sparse_prediction": false,
160
  "tie_word_embeddings": true,
161
  "transformers_version": "5.3.0",
 
162
  "use_cache": false,
163
+ "vocab_size": 50368
164
  }
open-pii-masking-500k-ai4privacy/TokenBased-CRF/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a2291ae713e208e7f762adbcbf6f6927ec7eb8be2dbeef176a6b54423d8c255
3
- size 711634067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c257c667c083dd911145530aa329c1ffd0eea0f9dee2d51a4f92ba73d3ed70
3
+ size 596251343
open-pii-masking-500k-ai4privacy/TokenBased-CRF/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
open-pii-masking-500k-ai4privacy/TokenBased-CRF/tokenizer_config.json CHANGED
@@ -1,15 +1,17 @@
1
  {
2
  "add_prefix_space": true,
3
  "backend": "tokenizers",
 
4
  "cls_token": "[CLS]",
5
- "do_lower_case": false,
6
  "is_local": false,
7
  "mask_token": "[MASK]",
8
- "model_max_length": 512,
 
 
 
 
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
  "unk_token": "[UNK]"
15
  }
 
1
  {
2
  "add_prefix_space": true,
3
  "backend": "tokenizers",
4
+ "clean_up_tokenization_spaces": true,
5
  "cls_token": "[CLS]",
 
6
  "is_local": false,
7
  "mask_token": "[MASK]",
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
  "pad_token": "[PAD]",
14
  "sep_token": "[SEP]",
15
+ "tokenizer_class": "TokenizersBackend",
 
 
16
  "unk_token": "[UNK]"
17
  }