hf-transformers-bot commited on
Commit
ad9c30a
·
verified ·
1 Parent(s): 9cea2eb

Update tiny models for OpenAIPrivacyFilterForTokenClassification

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +110 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +3 -0
  5. tokenizer_config.json +13 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OpenAIPrivacyFilterForTokenClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": 0.0,
9
+ "dtype": "float32",
10
+ "eos_token_id": 199999,
11
+ "head_dim": 8,
12
+ "hidden_size": 32,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-account_number",
16
+ "2": "I-account_number",
17
+ "3": "E-account_number",
18
+ "4": "S-account_number",
19
+ "5": "B-private_address",
20
+ "6": "I-private_address",
21
+ "7": "E-private_address",
22
+ "8": "S-private_address",
23
+ "9": "B-private_date",
24
+ "10": "I-private_date",
25
+ "11": "E-private_date",
26
+ "12": "S-private_date",
27
+ "13": "B-private_email",
28
+ "14": "I-private_email",
29
+ "15": "E-private_email",
30
+ "16": "S-private_email",
31
+ "17": "B-private_person",
32
+ "18": "I-private_person",
33
+ "19": "E-private_person",
34
+ "20": "S-private_person",
35
+ "21": "B-private_phone",
36
+ "22": "I-private_phone",
37
+ "23": "E-private_phone",
38
+ "24": "S-private_phone",
39
+ "25": "B-private_url",
40
+ "26": "I-private_url",
41
+ "27": "E-private_url",
42
+ "28": "S-private_url",
43
+ "29": "B-secret",
44
+ "30": "I-secret",
45
+ "31": "E-secret",
46
+ "32": "S-secret"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 16,
50
+ "label2id": {
51
+ "B-account_number": 1,
52
+ "B-private_address": 5,
53
+ "B-private_date": 9,
54
+ "B-private_email": 13,
55
+ "B-private_person": 17,
56
+ "B-private_phone": 21,
57
+ "B-private_url": 25,
58
+ "B-secret": 29,
59
+ "E-account_number": 3,
60
+ "E-private_address": 7,
61
+ "E-private_date": 11,
62
+ "E-private_email": 15,
63
+ "E-private_person": 19,
64
+ "E-private_phone": 23,
65
+ "E-private_url": 27,
66
+ "E-secret": 31,
67
+ "I-account_number": 2,
68
+ "I-private_address": 6,
69
+ "I-private_date": 10,
70
+ "I-private_email": 14,
71
+ "I-private_person": 18,
72
+ "I-private_phone": 22,
73
+ "I-private_url": 26,
74
+ "I-secret": 30,
75
+ "O": 0,
76
+ "S-account_number": 4,
77
+ "S-private_address": 8,
78
+ "S-private_date": 12,
79
+ "S-private_email": 16,
80
+ "S-private_person": 20,
81
+ "S-private_phone": 24,
82
+ "S-private_url": 28,
83
+ "S-secret": 32
84
+ },
85
+ "max_position_embeddings": 200,
86
+ "model_type": "openai_privacy_filter",
87
+ "num_attention_heads": 4,
88
+ "num_experts_per_tok": 2,
89
+ "num_hidden_layers": 2,
90
+ "num_key_value_heads": 2,
91
+ "num_local_experts": 4,
92
+ "output_router_logits": false,
93
+ "pad_token_id": 199999,
94
+ "rms_norm_eps": 1e-05,
95
+ "rope_parameters": {
96
+ "beta_fast": 32.0,
97
+ "beta_slow": 1.0,
98
+ "factor": 1.0,
99
+ "original_max_position_embeddings": 64,
100
+ "rope_theta": 150000.0,
101
+ "rope_type": "yarn",
102
+ "truncate": false
103
+ },
104
+ "router_aux_loss_coef": 0.001,
105
+ "sliding_window": 2,
106
+ "tie_word_embeddings": false,
107
+ "transformers_version": "5.16.0.dev0",
108
+ "use_cache": true,
109
+ "vocab_size": 200019
110
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e804a861957a2f72dd91d1b381243a459f5aed0fac1e8051e34d81a49a3a7f8
3
+ size 25689028
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
3
+ size 27868174
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "eos_token": "<|endoftext|>",
4
+ "is_local": true,
5
+ "local_files_only": false,
6
+ "model_input_names": [
7
+ "input_ids",
8
+ "attention_mask"
9
+ ],
10
+ "model_max_length": 200,
11
+ "pad_token": "<|endoftext|>",
12
+ "tokenizer_class": "TokenizersBackend"
13
+ }