Hugging Face's logo

PuxAI
/
GenPII-framework-Data

Safetensors
Model card Files
xet
 Community
PuxAI commited on
Commit
9b7401d
·
verified ·
1 Parent(s): 91f4541

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. gretel-pii-ready/TokenBased-CRF/checkpoint-63/config.json +66 -22
  2. gretel-pii-ready/TokenBased-CRF/checkpoint-63/model.safetensors +2 -2
  3. gretel-pii-ready/TokenBased-CRF/checkpoint-63/optimizer.pt +2 -2
  4. gretel-pii-ready/TokenBased-CRF/checkpoint-63/rng_state.pth +1 -1
  5. gretel-pii-ready/TokenBased-CRF/checkpoint-63/tokenizer.json +0 -0
  6. gretel-pii-ready/TokenBased-CRF/checkpoint-63/tokenizer_config.json +7 -5
  7. gretel-pii-ready/TokenBased-CRF/checkpoint-63/trainer_state.json +1 -1
  8. gretel-pii-ready/TokenBased-CRF/config.json +66 -22
  9. gretel-pii-ready/TokenBased-CRF/pytorch_model.bin +2 -2
  10. gretel-pii-ready/TokenBased-CRF/tokenizer.json +0 -0
  11. gretel-pii-ready/TokenBased-CRF/tokenizer_config.json +7 -5
gretel-pii-ready/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",
@@ -97,9 +104,9 @@
97
  "81": "B-VEHICLE_IDENTIFIER",
98
  "82": "I-VEHICLE_IDENTIFIER"
99
  },
 
100
  "initializer_range": 0.02,
101
- "intermediate_size": 3072,
102
- "is_decoder": false,
103
  "label2id": {
104
  "B-ACCOUNT_NUMBER": 1,
105
  "B-ADDRESS": 3,
@@ -185,20 +192,57 @@
185
  "I-VEHICLE_IDENTIFIER": 82,
186
  "O": 0
187
  },
188
- "layer_norm_eps": 1e-12,
189
- "max_position_embeddings": 512,
190
- "model_type": "bert",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
191
  "num_attention_heads": 12,
192
- "num_hidden_layers": 12,
193
- "pad_token_id": 0,
194
- "pooler_fc_size": 768,
195
- "pooler_num_attention_heads": 12,
196
- "pooler_num_fc_layers": 3,
197
- "pooler_size_per_head": 128,
198
- "pooler_type": "first_token_transform",
 
 
 
 
 
 
 
 
 
199
  "tie_word_embeddings": true,
200
  "transformers_version": "5.3.0",
201
- "type_vocab_size": 2,
202
  "use_cache": false,
203
- "vocab_size": 119547
204
  }
 
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",
 
104
  "81": "B-VEHICLE_IDENTIFIER",
105
  "82": "I-VEHICLE_IDENTIFIER"
106
  },
107
+ "initializer_cutoff_factor": 2.0,
108
  "initializer_range": 0.02,
109
+ "intermediate_size": 1152,
 
110
  "label2id": {
111
  "B-ACCOUNT_NUMBER": 1,
112
  "B-ADDRESS": 3,
 
192
  "I-VEHICLE_IDENTIFIER": 82,
193
  "O": 0
194
  },
195
+ "layer_norm_eps": 1e-05,
196
+ "layer_types": [
197
+ "full_attention",
198
+ "sliding_attention",
199
+ "sliding_attention",
200
+ "full_attention",
201
+ "sliding_attention",
202
+ "sliding_attention",
203
+ "full_attention",
204
+ "sliding_attention",
205
+ "sliding_attention",
206
+ "full_attention",
207
+ "sliding_attention",
208
+ "sliding_attention",
209
+ "full_attention",
210
+ "sliding_attention",
211
+ "sliding_attention",
212
+ "full_attention",
213
+ "sliding_attention",
214
+ "sliding_attention",
215
+ "full_attention",
216
+ "sliding_attention",
217
+ "sliding_attention",
218
+ "full_attention"
219
+ ],
220
+ "local_attention": 128,
221
+ "max_position_embeddings": 8192,
222
+ "mlp_bias": false,
223
+ "mlp_dropout": 0.0,
224
+ "model_type": "modernbert",
225
+ "norm_bias": false,
226
+ "norm_eps": 1e-05,
227
  "num_attention_heads": 12,
228
+ "num_hidden_layers": 22,
229
+ "pad_token_id": 50283,
230
+ "position_embedding_type": "absolute",
231
+ "rope_parameters": {
232
+ "full_attention": {
233
+ "rope_theta": 160000.0,
234
+ "rope_type": "default"
235
+ },
236
+ "sliding_attention": {
237
+ "rope_theta": 10000.0,
238
+ "rope_type": "default"
239
+ }
240
+ },
241
+ "sep_token_id": 50282,
242
+ "sparse_pred_ignore_index": -100,
243
+ "sparse_prediction": false,
244
  "tie_word_embeddings": true,
245
  "transformers_version": "5.3.0",
 
246
  "use_cache": false,
247
+ "vocab_size": 50368
248
  }
gretel-pii-ready/TokenBased-CRF/checkpoint-63/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:439798edc50763ad5fa5410fa6de9d93ec8113fae5b5c2af87888e17ec9d762a
3
- size 711722464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3674bfdf8d3174f264c7c764a2ab3ce41d23903a8c0dd1413a55f8f2396a714a
3
+ size 596355680
gretel-pii-ready/TokenBased-CRF/checkpoint-63/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddab49756ad4f6d019794d9313059edf9260a9dd99a2353fa29783859753da60
3
- size 1418841931
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c8de4b7b92956a8d68436bc4a50682baef47f4fbdd1798715f259315120e013
3
+ size 1192800523
gretel-pii-ready/TokenBased-CRF/checkpoint-63/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77e1bc0cc29528179cf7713b093fffbd0754c58c2875616aa74e1b6cd67bfe7d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7991aa545aa2a9819a120cc19b48bfbf88dcaec121a00f803b9fbabf38d57d55
3
  size 14645
gretel-pii-ready/TokenBased-CRF/checkpoint-63/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
gretel-pii-ready/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
  }
gretel-pii-ready/TokenBased-CRF/checkpoint-63/trainer_state.json CHANGED
@@ -26,7 +26,7 @@
26
  "attributes": {}
27
  }
28
  },
29
- "total_flos": 131662040064000.0,
30
  "train_batch_size": 8,
31
  "trial_name": null,
32
  "trial_params": null
 
26
  "attributes": {}
27
  }
28
  },
29
+ "total_flos": 169578286080000.0,
30
  "train_batch_size": 8,
31
  "trial_name": null,
32
  "trial_params": null
gretel-pii-ready/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",
@@ -97,9 +104,9 @@
97
  "81": "B-VEHICLE_IDENTIFIER",
98
  "82": "I-VEHICLE_IDENTIFIER"
99
  },
 
100
  "initializer_range": 0.02,
101
- "intermediate_size": 3072,
102
- "is_decoder": false,
103
  "label2id": {
104
  "B-ACCOUNT_NUMBER": 1,
105
  "B-ADDRESS": 3,
@@ -185,20 +192,57 @@
185
  "I-VEHICLE_IDENTIFIER": 82,
186
  "O": 0
187
  },
188
- "layer_norm_eps": 1e-12,
189
- "max_position_embeddings": 512,
190
- "model_type": "bert",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
191
  "num_attention_heads": 12,
192
- "num_hidden_layers": 12,
193
- "pad_token_id": 0,
194
- "pooler_fc_size": 768,
195
- "pooler_num_attention_heads": 12,
196
- "pooler_num_fc_layers": 3,
197
- "pooler_size_per_head": 128,
198
- "pooler_type": "first_token_transform",
 
 
 
 
 
 
 
 
 
199
  "tie_word_embeddings": true,
200
  "transformers_version": "5.3.0",
201
- "type_vocab_size": 2,
202
  "use_cache": false,
203
- "vocab_size": 119547
204
  }
 
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",
 
104
  "81": "B-VEHICLE_IDENTIFIER",
105
  "82": "I-VEHICLE_IDENTIFIER"
106
  },
107
+ "initializer_cutoff_factor": 2.0,
108
  "initializer_range": 0.02,
109
+ "intermediate_size": 1152,
 
110
  "label2id": {
111
  "B-ACCOUNT_NUMBER": 1,
112
  "B-ADDRESS": 3,
 
192
  "I-VEHICLE_IDENTIFIER": 82,
193
  "O": 0
194
  },
195
+ "layer_norm_eps": 1e-05,
196
+ "layer_types": [
197
+ "full_attention",
198
+ "sliding_attention",
199
+ "sliding_attention",
200
+ "full_attention",
201
+ "sliding_attention",
202
+ "sliding_attention",
203
+ "full_attention",
204
+ "sliding_attention",
205
+ "sliding_attention",
206
+ "full_attention",
207
+ "sliding_attention",
208
+ "sliding_attention",
209
+ "full_attention",
210
+ "sliding_attention",
211
+ "sliding_attention",
212
+ "full_attention",
213
+ "sliding_attention",
214
+ "sliding_attention",
215
+ "full_attention",
216
+ "sliding_attention",
217
+ "sliding_attention",
218
+ "full_attention"
219
+ ],
220
+ "local_attention": 128,
221
+ "max_position_embeddings": 8192,
222
+ "mlp_bias": false,
223
+ "mlp_dropout": 0.0,
224
+ "model_type": "modernbert",
225
+ "norm_bias": false,
226
+ "norm_eps": 1e-05,
227
  "num_attention_heads": 12,
228
+ "num_hidden_layers": 22,
229
+ "pad_token_id": 50283,
230
+ "position_embedding_type": "absolute",
231
+ "rope_parameters": {
232
+ "full_attention": {
233
+ "rope_theta": 160000.0,
234
+ "rope_type": "default"
235
+ },
236
+ "sliding_attention": {
237
+ "rope_theta": 10000.0,
238
+ "rope_type": "default"
239
+ }
240
+ },
241
+ "sep_token_id": 50282,
242
+ "sparse_pred_ignore_index": -100,
243
+ "sparse_prediction": false,
244
  "tie_word_embeddings": true,
245
  "transformers_version": "5.3.0",
 
246
  "use_cache": false,
247
+ "vocab_size": 50368
248
  }
gretel-pii-ready/TokenBased-CRF/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebf6fa05e9ef79aacd8d79dd484d2d564ec9be20273c94f7c8cc167ea383afdf
3
- size 711784467
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518c0d9525653860285e6b25047e0052a4c6f1896a88959b99cf9b29d2af3acc
3
+ size 596401743
gretel-pii-ready/TokenBased-CRF/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
gretel-pii-ready/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
  }