Hugging Face's logo

PuxAI
/
GenPII-framework-Data

Safetensors
Model card Files
xet
 Community
PuxAI commited on
Commit
98d3ba8
·
verified ·
1 Parent(s): c4f316c

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. nemotron-pii-ready/TokenBased-CRF/checkpoint-63/config.json +22 -66
  2. nemotron-pii-ready/TokenBased-CRF/checkpoint-63/model.safetensors +2 -2
  3. nemotron-pii-ready/TokenBased-CRF/checkpoint-63/optimizer.pt +2 -2
  4. nemotron-pii-ready/TokenBased-CRF/checkpoint-63/rng_state.pth +1 -1
  5. nemotron-pii-ready/TokenBased-CRF/checkpoint-63/tokenizer.json +0 -0
  6. nemotron-pii-ready/TokenBased-CRF/checkpoint-63/tokenizer_config.json +5 -7
  7. nemotron-pii-ready/TokenBased-CRF/checkpoint-63/trainer_state.json +1 -1
  8. nemotron-pii-ready/TokenBased-CRF/config.json +22 -66
  9. nemotron-pii-ready/TokenBased-CRF/pytorch_model.bin +2 -2
  10. nemotron-pii-ready/TokenBased-CRF/tokenizer.json +0 -0
  11. nemotron-pii-ready/TokenBased-CRF/tokenizer_config.json +5 -7
nemotron-pii-ready/TokenBased-CRF/checkpoint-63/config.json CHANGED
@@ -1,23 +1,16 @@
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",
@@ -130,9 +123,9 @@
130
  "107": "B-VEHICLE_IDENTIFIER",
131
  "108": "I-VEHICLE_IDENTIFIER"
132
  },
133
- "initializer_cutoff_factor": 2.0,
134
  "initializer_range": 0.02,
135
- "intermediate_size": 1152,
 
136
  "label2id": {
137
  "B-ACCOUNT_NUMBER": 1,
138
  "B-AGE": 3,
@@ -244,57 +237,20 @@
244
  "I-VEHICLE_IDENTIFIER": 108,
245
  "O": 0
246
  },
247
- "layer_norm_eps": 1e-05,
248
- "layer_types": [
249
- "full_attention",
250
- "sliding_attention",
251
- "sliding_attention",
252
- "full_attention",
253
- "sliding_attention",
254
- "sliding_attention",
255
- "full_attention",
256
- "sliding_attention",
257
- "sliding_attention",
258
- "full_attention",
259
- "sliding_attention",
260
- "sliding_attention",
261
- "full_attention",
262
- "sliding_attention",
263
- "sliding_attention",
264
- "full_attention",
265
- "sliding_attention",
266
- "sliding_attention",
267
- "full_attention",
268
- "sliding_attention",
269
- "sliding_attention",
270
- "full_attention"
271
- ],
272
- "local_attention": 128,
273
- "max_position_embeddings": 8192,
274
- "mlp_bias": false,
275
- "mlp_dropout": 0.0,
276
- "model_type": "modernbert",
277
- "norm_bias": false,
278
- "norm_eps": 1e-05,
279
  "num_attention_heads": 12,
280
- "num_hidden_layers": 22,
281
- "pad_token_id": 50283,
282
- "position_embedding_type": "absolute",
283
- "rope_parameters": {
284
- "full_attention": {
285
- "rope_theta": 160000.0,
286
- "rope_type": "default"
287
- },
288
- "sliding_attention": {
289
- "rope_theta": 10000.0,
290
- "rope_type": "default"
291
- }
292
- },
293
- "sep_token_id": 50282,
294
- "sparse_pred_ignore_index": -100,
295
- "sparse_prediction": false,
296
  "tie_word_embeddings": true,
297
  "transformers_version": "5.3.0",
 
298
  "use_cache": false,
299
- "vocab_size": 50368
300
  }
 
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",
 
123
  "107": "B-VEHICLE_IDENTIFIER",
124
  "108": "I-VEHICLE_IDENTIFIER"
125
  },
 
126
  "initializer_range": 0.02,
127
+ "intermediate_size": 3072,
128
+ "is_decoder": false,
129
  "label2id": {
130
  "B-ACCOUNT_NUMBER": 1,
131
  "B-AGE": 3,
 
237
  "I-VEHICLE_IDENTIFIER": 108,
238
  "O": 0
239
  },
240
+ "layer_norm_eps": 1e-12,
241
+ "max_position_embeddings": 512,
242
+ "model_type": "bert",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
243
  "num_attention_heads": 12,
244
+ "num_hidden_layers": 12,
245
+ "pad_token_id": 0,
246
+ "pooler_fc_size": 768,
247
+ "pooler_num_attention_heads": 12,
248
+ "pooler_num_fc_layers": 3,
249
+ "pooler_size_per_head": 128,
250
+ "pooler_type": "first_token_transform",
 
 
 
 
 
 
 
 
 
251
  "tie_word_embeddings": true,
252
  "transformers_version": "5.3.0",
253
+ "type_vocab_size": 2,
254
  "use_cache": false,
255
+ "vocab_size": 119547
256
  }
nemotron-pii-ready/TokenBased-CRF/checkpoint-63/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c1802035d0054e1a44669277b78b110c5a9ea8158a3c48bcf02c3a9d16b85cc
3
- size 596455840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08d1ac8aa8d053477a6f88bfbc10972386877e64f69109bde11da057440e0961
3
+ size 711822624
nemotron-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:e77298b7bc60069305b811f1bd9c931c86911524ef1e779a3d253dea66b65263
3
- size 1193000587
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51eb37cc352c9df7416b2fc4c276ace2c75c2dfae431da816de08f21e303939
3
+ size 1419041995
nemotron-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 sha256:7991aa545aa2a9819a120cc19b48bfbf88dcaec121a00f803b9fbabf38d57d55
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e1bc0cc29528179cf7713b093fffbd0754c58c2875616aa74e1b6cd67bfe7d
3
  size 14645
nemotron-pii-ready/TokenBased-CRF/checkpoint-63/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
nemotron-pii-ready/TokenBased-CRF/checkpoint-63/tokenizer_config.json CHANGED
@@ -1,17 +1,15 @@
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
  }
 
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
  }
nemotron-pii-ready/TokenBased-CRF/checkpoint-63/trainer_state.json CHANGED
@@ -26,7 +26,7 @@
26
  "attributes": {}
27
  }
28
  },
29
- "total_flos": 169616744448000.0,
30
  "train_batch_size": 8,
31
  "trial_name": null,
32
  "trial_params": null
 
26
  "attributes": {}
27
  }
28
  },
29
+ "total_flos": 131700498432000.0,
30
  "train_batch_size": 8,
31
  "trial_name": null,
32
  "trial_params": null
nemotron-pii-ready/TokenBased-CRF/config.json CHANGED
@@ -1,23 +1,16 @@
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",
@@ -130,9 +123,9 @@
130
  "107": "B-VEHICLE_IDENTIFIER",
131
  "108": "I-VEHICLE_IDENTIFIER"
132
  },
133
- "initializer_cutoff_factor": 2.0,
134
  "initializer_range": 0.02,
135
- "intermediate_size": 1152,
 
136
  "label2id": {
137
  "B-ACCOUNT_NUMBER": 1,
138
  "B-AGE": 3,
@@ -244,57 +237,20 @@
244
  "I-VEHICLE_IDENTIFIER": 108,
245
  "O": 0
246
  },
247
- "layer_norm_eps": 1e-05,
248
- "layer_types": [
249
- "full_attention",
250
- "sliding_attention",
251
- "sliding_attention",
252
- "full_attention",
253
- "sliding_attention",
254
- "sliding_attention",
255
- "full_attention",
256
- "sliding_attention",
257
- "sliding_attention",
258
- "full_attention",
259
- "sliding_attention",
260
- "sliding_attention",
261
- "full_attention",
262
- "sliding_attention",
263
- "sliding_attention",
264
- "full_attention",
265
- "sliding_attention",
266
- "sliding_attention",
267
- "full_attention",
268
- "sliding_attention",
269
- "sliding_attention",
270
- "full_attention"
271
- ],
272
- "local_attention": 128,
273
- "max_position_embeddings": 8192,
274
- "mlp_bias": false,
275
- "mlp_dropout": 0.0,
276
- "model_type": "modernbert",
277
- "norm_bias": false,
278
- "norm_eps": 1e-05,
279
  "num_attention_heads": 12,
280
- "num_hidden_layers": 22,
281
- "pad_token_id": 50283,
282
- "position_embedding_type": "absolute",
283
- "rope_parameters": {
284
- "full_attention": {
285
- "rope_theta": 160000.0,
286
- "rope_type": "default"
287
- },
288
- "sliding_attention": {
289
- "rope_theta": 10000.0,
290
- "rope_type": "default"
291
- }
292
- },
293
- "sep_token_id": 50282,
294
- "sparse_pred_ignore_index": -100,
295
- "sparse_prediction": false,
296
  "tie_word_embeddings": true,
297
  "transformers_version": "5.3.0",
 
298
  "use_cache": false,
299
- "vocab_size": 50368
300
  }
 
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",
 
123
  "107": "B-VEHICLE_IDENTIFIER",
124
  "108": "I-VEHICLE_IDENTIFIER"
125
  },
 
126
  "initializer_range": 0.02,
127
+ "intermediate_size": 3072,
128
+ "is_decoder": false,
129
  "label2id": {
130
  "B-ACCOUNT_NUMBER": 1,
131
  "B-AGE": 3,
 
237
  "I-VEHICLE_IDENTIFIER": 108,
238
  "O": 0
239
  },
240
+ "layer_norm_eps": 1e-12,
241
+ "max_position_embeddings": 512,
242
+ "model_type": "bert",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
243
  "num_attention_heads": 12,
244
+ "num_hidden_layers": 12,
245
+ "pad_token_id": 0,
246
+ "pooler_fc_size": 768,
247
+ "pooler_num_attention_heads": 12,
248
+ "pooler_num_fc_layers": 3,
249
+ "pooler_size_per_head": 128,
250
+ "pooler_type": "first_token_transform",
 
 
 
 
 
 
 
 
 
251
  "tie_word_embeddings": true,
252
  "transformers_version": "5.3.0",
253
+ "type_vocab_size": 2,
254
  "use_cache": false,
255
+ "vocab_size": 119547
256
  }
nemotron-pii-ready/TokenBased-CRF/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98a38602a77f55edb616334fefea94ccbb682f09b9d9f3f2ef94be364cb4c8a9
3
- size 596501775
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6bc807c5941b759066c4f6f5499c62fcb0e7471255caba1aa1b887d6a48c4c2
3
+ size 711884499
nemotron-pii-ready/TokenBased-CRF/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
nemotron-pii-ready/TokenBased-CRF/tokenizer_config.json CHANGED
@@ -1,17 +1,15 @@
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
  }
 
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
  }