Token Classification
Transformers
ONNX
Turkish
bert
privacy
pii
kvkk
turkish
named-entity-recognition
data-redaction
privacy-filter
runeward
int8
Instructions to use curiositytech/runeward-small-onnx-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use curiositytech/runeward-small-onnx-int8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="curiositytech/runeward-small-onnx-int8")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("curiositytech/runeward-small-onnx-int8") model = AutoModelForTokenClassification.from_pretrained("curiositytech/runeward-small-onnx-int8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload Runeward Small ONNX INT8 CPU model
Browse files- config.json +118 -0
- model_quantized.onnx +3 -0
- ort_config.json +33 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-private_person",
|
| 14 |
+
"2": "I-private_person",
|
| 15 |
+
"3": "B-private_email",
|
| 16 |
+
"4": "I-private_email",
|
| 17 |
+
"5": "B-private_phone",
|
| 18 |
+
"6": "I-private_phone",
|
| 19 |
+
"7": "B-private_address",
|
| 20 |
+
"8": "I-private_address",
|
| 21 |
+
"9": "B-private_date",
|
| 22 |
+
"10": "I-private_date",
|
| 23 |
+
"11": "B-private_url",
|
| 24 |
+
"12": "I-private_url",
|
| 25 |
+
"13": "B-account_number",
|
| 26 |
+
"14": "I-account_number",
|
| 27 |
+
"15": "B-secret",
|
| 28 |
+
"16": "I-secret",
|
| 29 |
+
"17": "B-tckn",
|
| 30 |
+
"18": "I-tckn",
|
| 31 |
+
"19": "B-iban",
|
| 32 |
+
"20": "I-iban",
|
| 33 |
+
"21": "B-tax_number",
|
| 34 |
+
"22": "I-tax_number",
|
| 35 |
+
"23": "B-passport_number",
|
| 36 |
+
"24": "I-passport_number",
|
| 37 |
+
"25": "B-license_plate",
|
| 38 |
+
"26": "I-license_plate",
|
| 39 |
+
"27": "B-credit_card",
|
| 40 |
+
"28": "I-credit_card",
|
| 41 |
+
"29": "B-health_data",
|
| 42 |
+
"30": "I-health_data",
|
| 43 |
+
"31": "B-biometric_data",
|
| 44 |
+
"32": "I-biometric_data",
|
| 45 |
+
"33": "B-genetic_data",
|
| 46 |
+
"34": "I-genetic_data",
|
| 47 |
+
"35": "B-religion_or_belief",
|
| 48 |
+
"36": "I-religion_or_belief",
|
| 49 |
+
"37": "B-political_opinion",
|
| 50 |
+
"38": "I-political_opinion",
|
| 51 |
+
"39": "B-union_membership",
|
| 52 |
+
"40": "I-union_membership",
|
| 53 |
+
"41": "B-criminal_record",
|
| 54 |
+
"42": "I-criminal_record",
|
| 55 |
+
"43": "B-child_data",
|
| 56 |
+
"44": "I-child_data"
|
| 57 |
+
},
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 3072,
|
| 60 |
+
"label2id": {
|
| 61 |
+
"B-account_number": 13,
|
| 62 |
+
"B-biometric_data": 31,
|
| 63 |
+
"B-child_data": 43,
|
| 64 |
+
"B-credit_card": 27,
|
| 65 |
+
"B-criminal_record": 41,
|
| 66 |
+
"B-genetic_data": 33,
|
| 67 |
+
"B-health_data": 29,
|
| 68 |
+
"B-iban": 19,
|
| 69 |
+
"B-license_plate": 25,
|
| 70 |
+
"B-passport_number": 23,
|
| 71 |
+
"B-political_opinion": 37,
|
| 72 |
+
"B-private_address": 7,
|
| 73 |
+
"B-private_date": 9,
|
| 74 |
+
"B-private_email": 3,
|
| 75 |
+
"B-private_person": 1,
|
| 76 |
+
"B-private_phone": 5,
|
| 77 |
+
"B-private_url": 11,
|
| 78 |
+
"B-religion_or_belief": 35,
|
| 79 |
+
"B-secret": 15,
|
| 80 |
+
"B-tax_number": 21,
|
| 81 |
+
"B-tckn": 17,
|
| 82 |
+
"B-union_membership": 39,
|
| 83 |
+
"I-account_number": 14,
|
| 84 |
+
"I-biometric_data": 32,
|
| 85 |
+
"I-child_data": 44,
|
| 86 |
+
"I-credit_card": 28,
|
| 87 |
+
"I-criminal_record": 42,
|
| 88 |
+
"I-genetic_data": 34,
|
| 89 |
+
"I-health_data": 30,
|
| 90 |
+
"I-iban": 20,
|
| 91 |
+
"I-license_plate": 26,
|
| 92 |
+
"I-passport_number": 24,
|
| 93 |
+
"I-political_opinion": 38,
|
| 94 |
+
"I-private_address": 8,
|
| 95 |
+
"I-private_date": 10,
|
| 96 |
+
"I-private_email": 4,
|
| 97 |
+
"I-private_person": 2,
|
| 98 |
+
"I-private_phone": 6,
|
| 99 |
+
"I-private_url": 12,
|
| 100 |
+
"I-religion_or_belief": 36,
|
| 101 |
+
"I-secret": 16,
|
| 102 |
+
"I-tax_number": 22,
|
| 103 |
+
"I-tckn": 18,
|
| 104 |
+
"I-union_membership": 40,
|
| 105 |
+
"O": 0
|
| 106 |
+
},
|
| 107 |
+
"layer_norm_eps": 1e-12,
|
| 108 |
+
"max_position_embeddings": 512,
|
| 109 |
+
"model_type": "bert",
|
| 110 |
+
"num_attention_heads": 12,
|
| 111 |
+
"num_hidden_layers": 12,
|
| 112 |
+
"pad_token_id": 0,
|
| 113 |
+
"position_embedding_type": "absolute",
|
| 114 |
+
"transformers_version": "4.57.6",
|
| 115 |
+
"type_vocab_size": 2,
|
| 116 |
+
"use_cache": true,
|
| 117 |
+
"vocab_size": 32000
|
| 118 |
+
}
|
model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df40fc234f5363aa1f950e816520d1b6fb7ba7cef99653f32e078ec091753c5c
|
| 3 |
+
size 110854526
|
ort_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"one_external_file": true,
|
| 3 |
+
"opset": null,
|
| 4 |
+
"optimization": {},
|
| 5 |
+
"quantization": {
|
| 6 |
+
"activations_dtype": "QUInt8",
|
| 7 |
+
"activations_symmetric": false,
|
| 8 |
+
"format": "QOperator",
|
| 9 |
+
"is_static": false,
|
| 10 |
+
"mode": "IntegerOps",
|
| 11 |
+
"nodes_to_exclude": [],
|
| 12 |
+
"nodes_to_quantize": [],
|
| 13 |
+
"operators_to_quantize": [
|
| 14 |
+
"Conv",
|
| 15 |
+
"MatMul",
|
| 16 |
+
"Attention",
|
| 17 |
+
"LSTM",
|
| 18 |
+
"Gather",
|
| 19 |
+
"Transpose",
|
| 20 |
+
"EmbedLayerNormalization"
|
| 21 |
+
],
|
| 22 |
+
"per_channel": false,
|
| 23 |
+
"qdq_add_pair_to_weight": false,
|
| 24 |
+
"qdq_dedicated_pair": false,
|
| 25 |
+
"qdq_op_type_per_channel_support_to_axis": {
|
| 26 |
+
"MatMul": 1
|
| 27 |
+
},
|
| 28 |
+
"reduce_range": false,
|
| 29 |
+
"weights_dtype": "QUInt8",
|
| 30 |
+
"weights_symmetric": true
|
| 31 |
+
},
|
| 32 |
+
"use_external_data_format": false
|
| 33 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"max_len": 512,
|
| 51 |
+
"max_length": 256,
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"never_split": null,
|
| 54 |
+
"pad_token": "[PAD]",
|
| 55 |
+
"sep_token": "[SEP]",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"strip_accents": null,
|
| 58 |
+
"tokenize_chinese_chars": true,
|
| 59 |
+
"tokenizer_class": "BertTokenizer",
|
| 60 |
+
"truncation_side": "right",
|
| 61 |
+
"truncation_strategy": "longest_first",
|
| 62 |
+
"unk_token": "[UNK]"
|
| 63 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|