Upload folder using huggingface_hub
Browse files- README.md +9 -0
- config.json +251 -0
- onnx/model.onnx +3 -0
- onnx/model_bnb4.onnx +3 -0
- onnx/model_fp16.onnx +3 -0
- onnx/model_int8.onnx +3 -0
- onnx/model_q4.onnx +3 -0
- onnx/model_q4f16.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- onnx/model_uint8.onnx +3 -0
- quantize_config.json +18 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers.js
|
| 3 |
+
base_model:
|
| 4 |
+
- Isotonic/distilbert_finetuned_ai4privacy_v2
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# distilbert_finetuned_ai4privacy_v2 (ONNX)
|
| 8 |
+
|
| 9 |
+
This is an ONNX version of [Isotonic/distilbert_finetuned_ai4privacy_v2](https://huggingface.co/Isotonic/distilbert_finetuned_ai4privacy_v2). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
|
config.json
ADDED
|
@@ -0,0 +1,251 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "Isotonic/distilbert_finetuned_ai4privacy_v2",
|
| 4 |
+
"activation": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"DistilBertForTokenClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"dim": 768,
|
| 10 |
+
"dropout": 0.1,
|
| 11 |
+
"hidden_dim": 3072,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "O",
|
| 14 |
+
"1": "B-PHONEIMEI",
|
| 15 |
+
"2": "I-PHONEIMEI",
|
| 16 |
+
"3": "B-JOBAREA",
|
| 17 |
+
"4": "B-FIRSTNAME",
|
| 18 |
+
"5": "I-FIRSTNAME",
|
| 19 |
+
"6": "B-VEHICLEVIN",
|
| 20 |
+
"7": "I-VEHICLEVIN",
|
| 21 |
+
"8": "B-AGE",
|
| 22 |
+
"9": "B-GENDER",
|
| 23 |
+
"10": "I-GENDER",
|
| 24 |
+
"11": "B-HEIGHT",
|
| 25 |
+
"12": "I-HEIGHT",
|
| 26 |
+
"13": "B-BUILDINGNUMBER",
|
| 27 |
+
"14": "I-BUILDINGNUMBER",
|
| 28 |
+
"15": "B-MASKEDNUMBER",
|
| 29 |
+
"16": "I-MASKEDNUMBER",
|
| 30 |
+
"17": "B-PASSWORD",
|
| 31 |
+
"18": "I-PASSWORD",
|
| 32 |
+
"19": "B-DOB",
|
| 33 |
+
"20": "I-DOB",
|
| 34 |
+
"21": "B-IPV6",
|
| 35 |
+
"22": "I-IPV6",
|
| 36 |
+
"23": "B-NEARBYGPSCOORDINATE",
|
| 37 |
+
"24": "I-NEARBYGPSCOORDINATE",
|
| 38 |
+
"25": "B-USERAGENT",
|
| 39 |
+
"26": "I-USERAGENT",
|
| 40 |
+
"27": "B-TIME",
|
| 41 |
+
"28": "I-TIME",
|
| 42 |
+
"29": "B-JOBTITLE",
|
| 43 |
+
"30": "I-JOBTITLE",
|
| 44 |
+
"31": "B-COUNTY",
|
| 45 |
+
"32": "B-EMAIL",
|
| 46 |
+
"33": "I-EMAIL",
|
| 47 |
+
"34": "B-ACCOUNTNUMBER",
|
| 48 |
+
"35": "I-ACCOUNTNUMBER",
|
| 49 |
+
"36": "B-PIN",
|
| 50 |
+
"37": "I-PIN",
|
| 51 |
+
"38": "B-EYECOLOR",
|
| 52 |
+
"39": "I-EYECOLOR",
|
| 53 |
+
"40": "B-LASTNAME",
|
| 54 |
+
"41": "I-LASTNAME",
|
| 55 |
+
"42": "I-JOBAREA",
|
| 56 |
+
"43": "B-IPV4",
|
| 57 |
+
"44": "I-IPV4",
|
| 58 |
+
"45": "B-DATE",
|
| 59 |
+
"46": "I-DATE",
|
| 60 |
+
"47": "B-STREET",
|
| 61 |
+
"48": "I-STREET",
|
| 62 |
+
"49": "B-CITY",
|
| 63 |
+
"50": "I-CITY",
|
| 64 |
+
"51": "B-PREFIX",
|
| 65 |
+
"52": "I-PREFIX",
|
| 66 |
+
"53": "B-CREDITCARDISSUER",
|
| 67 |
+
"54": "B-CREDITCARDNUMBER",
|
| 68 |
+
"55": "I-CREDITCARDNUMBER",
|
| 69 |
+
"56": "I-CREDITCARDISSUER",
|
| 70 |
+
"57": "B-MIDDLENAME",
|
| 71 |
+
"58": "B-STATE",
|
| 72 |
+
"59": "I-STATE",
|
| 73 |
+
"60": "B-VEHICLEVRM",
|
| 74 |
+
"61": "I-VEHICLEVRM",
|
| 75 |
+
"62": "B-ORDINALDIRECTION",
|
| 76 |
+
"63": "B-SEX",
|
| 77 |
+
"64": "B-JOBTYPE",
|
| 78 |
+
"65": "I-JOBTYPE",
|
| 79 |
+
"66": "B-CURRENCYCODE",
|
| 80 |
+
"67": "I-CURRENCYCODE",
|
| 81 |
+
"68": "B-CURRENCYSYMBOL",
|
| 82 |
+
"69": "I-AMOUNT",
|
| 83 |
+
"70": "B-ACCOUNTNAME",
|
| 84 |
+
"71": "I-ACCOUNTNAME",
|
| 85 |
+
"72": "B-BITCOINADDRESS",
|
| 86 |
+
"73": "I-BITCOINADDRESS",
|
| 87 |
+
"74": "B-LITECOINADDRESS",
|
| 88 |
+
"75": "I-LITECOINADDRESS",
|
| 89 |
+
"76": "B-PHONENUMBER",
|
| 90 |
+
"77": "I-PHONENUMBER",
|
| 91 |
+
"78": "B-MAC",
|
| 92 |
+
"79": "I-MAC",
|
| 93 |
+
"80": "B-CURRENCY",
|
| 94 |
+
"81": "B-IBAN",
|
| 95 |
+
"82": "I-IBAN",
|
| 96 |
+
"83": "B-COMPANYNAME",
|
| 97 |
+
"84": "I-COMPANYNAME",
|
| 98 |
+
"85": "B-CURRENCYNAME",
|
| 99 |
+
"86": "I-CURRENCYNAME",
|
| 100 |
+
"87": "I-CURRENCYSYMBOL",
|
| 101 |
+
"88": "B-ZIPCODE",
|
| 102 |
+
"89": "I-ZIPCODE",
|
| 103 |
+
"90": "B-SSN",
|
| 104 |
+
"91": "I-SSN",
|
| 105 |
+
"92": "B-AMOUNT",
|
| 106 |
+
"93": "I-CURRENCY",
|
| 107 |
+
"94": "B-URL",
|
| 108 |
+
"95": "I-URL",
|
| 109 |
+
"96": "B-IP",
|
| 110 |
+
"97": "I-IP",
|
| 111 |
+
"98": "B-SECONDARYADDRESS",
|
| 112 |
+
"99": "I-SECONDARYADDRESS",
|
| 113 |
+
"100": "B-USERNAME",
|
| 114 |
+
"101": "I-USERNAME",
|
| 115 |
+
"102": "B-ETHEREUMADDRESS",
|
| 116 |
+
"103": "I-ETHEREUMADDRESS",
|
| 117 |
+
"104": "B-CREDITCARDCVV",
|
| 118 |
+
"105": "I-CREDITCARDCVV",
|
| 119 |
+
"106": "I-COUNTY",
|
| 120 |
+
"107": "I-AGE",
|
| 121 |
+
"108": "I-MIDDLENAME",
|
| 122 |
+
"109": "B-BIC",
|
| 123 |
+
"110": "I-BIC"
|
| 124 |
+
},
|
| 125 |
+
"initializer_range": 0.02,
|
| 126 |
+
"label2id": {
|
| 127 |
+
"B-ACCOUNTNAME": 70,
|
| 128 |
+
"B-ACCOUNTNUMBER": 34,
|
| 129 |
+
"B-AGE": 8,
|
| 130 |
+
"B-AMOUNT": 92,
|
| 131 |
+
"B-BIC": 109,
|
| 132 |
+
"B-BITCOINADDRESS": 72,
|
| 133 |
+
"B-BUILDINGNUMBER": 13,
|
| 134 |
+
"B-CITY": 49,
|
| 135 |
+
"B-COMPANYNAME": 83,
|
| 136 |
+
"B-COUNTY": 31,
|
| 137 |
+
"B-CREDITCARDCVV": 104,
|
| 138 |
+
"B-CREDITCARDISSUER": 53,
|
| 139 |
+
"B-CREDITCARDNUMBER": 54,
|
| 140 |
+
"B-CURRENCY": 80,
|
| 141 |
+
"B-CURRENCYCODE": 66,
|
| 142 |
+
"B-CURRENCYNAME": 85,
|
| 143 |
+
"B-CURRENCYSYMBOL": 68,
|
| 144 |
+
"B-DATE": 45,
|
| 145 |
+
"B-DOB": 19,
|
| 146 |
+
"B-EMAIL": 32,
|
| 147 |
+
"B-ETHEREUMADDRESS": 102,
|
| 148 |
+
"B-EYECOLOR": 38,
|
| 149 |
+
"B-FIRSTNAME": 4,
|
| 150 |
+
"B-GENDER": 9,
|
| 151 |
+
"B-HEIGHT": 11,
|
| 152 |
+
"B-IBAN": 81,
|
| 153 |
+
"B-IP": 96,
|
| 154 |
+
"B-IPV4": 43,
|
| 155 |
+
"B-IPV6": 21,
|
| 156 |
+
"B-JOBAREA": 3,
|
| 157 |
+
"B-JOBTITLE": 29,
|
| 158 |
+
"B-JOBTYPE": 64,
|
| 159 |
+
"B-LASTNAME": 40,
|
| 160 |
+
"B-LITECOINADDRESS": 74,
|
| 161 |
+
"B-MAC": 78,
|
| 162 |
+
"B-MASKEDNUMBER": 15,
|
| 163 |
+
"B-MIDDLENAME": 57,
|
| 164 |
+
"B-NEARBYGPSCOORDINATE": 23,
|
| 165 |
+
"B-ORDINALDIRECTION": 62,
|
| 166 |
+
"B-PASSWORD": 17,
|
| 167 |
+
"B-PHONEIMEI": 1,
|
| 168 |
+
"B-PHONENUMBER": 76,
|
| 169 |
+
"B-PIN": 36,
|
| 170 |
+
"B-PREFIX": 51,
|
| 171 |
+
"B-SECONDARYADDRESS": 98,
|
| 172 |
+
"B-SEX": 63,
|
| 173 |
+
"B-SSN": 90,
|
| 174 |
+
"B-STATE": 58,
|
| 175 |
+
"B-STREET": 47,
|
| 176 |
+
"B-TIME": 27,
|
| 177 |
+
"B-URL": 94,
|
| 178 |
+
"B-USERAGENT": 25,
|
| 179 |
+
"B-USERNAME": 100,
|
| 180 |
+
"B-VEHICLEVIN": 6,
|
| 181 |
+
"B-VEHICLEVRM": 60,
|
| 182 |
+
"B-ZIPCODE": 88,
|
| 183 |
+
"I-ACCOUNTNAME": 71,
|
| 184 |
+
"I-ACCOUNTNUMBER": 35,
|
| 185 |
+
"I-AGE": 107,
|
| 186 |
+
"I-AMOUNT": 69,
|
| 187 |
+
"I-BIC": 110,
|
| 188 |
+
"I-BITCOINADDRESS": 73,
|
| 189 |
+
"I-BUILDINGNUMBER": 14,
|
| 190 |
+
"I-CITY": 50,
|
| 191 |
+
"I-COMPANYNAME": 84,
|
| 192 |
+
"I-COUNTY": 106,
|
| 193 |
+
"I-CREDITCARDCVV": 105,
|
| 194 |
+
"I-CREDITCARDISSUER": 56,
|
| 195 |
+
"I-CREDITCARDNUMBER": 55,
|
| 196 |
+
"I-CURRENCY": 93,
|
| 197 |
+
"I-CURRENCYCODE": 67,
|
| 198 |
+
"I-CURRENCYNAME": 86,
|
| 199 |
+
"I-CURRENCYSYMBOL": 87,
|
| 200 |
+
"I-DATE": 46,
|
| 201 |
+
"I-DOB": 20,
|
| 202 |
+
"I-EMAIL": 33,
|
| 203 |
+
"I-ETHEREUMADDRESS": 103,
|
| 204 |
+
"I-EYECOLOR": 39,
|
| 205 |
+
"I-FIRSTNAME": 5,
|
| 206 |
+
"I-GENDER": 10,
|
| 207 |
+
"I-HEIGHT": 12,
|
| 208 |
+
"I-IBAN": 82,
|
| 209 |
+
"I-IP": 97,
|
| 210 |
+
"I-IPV4": 44,
|
| 211 |
+
"I-IPV6": 22,
|
| 212 |
+
"I-JOBAREA": 42,
|
| 213 |
+
"I-JOBTITLE": 30,
|
| 214 |
+
"I-JOBTYPE": 65,
|
| 215 |
+
"I-LASTNAME": 41,
|
| 216 |
+
"I-LITECOINADDRESS": 75,
|
| 217 |
+
"I-MAC": 79,
|
| 218 |
+
"I-MASKEDNUMBER": 16,
|
| 219 |
+
"I-MIDDLENAME": 108,
|
| 220 |
+
"I-NEARBYGPSCOORDINATE": 24,
|
| 221 |
+
"I-PASSWORD": 18,
|
| 222 |
+
"I-PHONEIMEI": 2,
|
| 223 |
+
"I-PHONENUMBER": 77,
|
| 224 |
+
"I-PIN": 37,
|
| 225 |
+
"I-PREFIX": 52,
|
| 226 |
+
"I-SECONDARYADDRESS": 99,
|
| 227 |
+
"I-SSN": 91,
|
| 228 |
+
"I-STATE": 59,
|
| 229 |
+
"I-STREET": 48,
|
| 230 |
+
"I-TIME": 28,
|
| 231 |
+
"I-URL": 95,
|
| 232 |
+
"I-USERAGENT": 26,
|
| 233 |
+
"I-USERNAME": 101,
|
| 234 |
+
"I-VEHICLEVIN": 7,
|
| 235 |
+
"I-VEHICLEVRM": 61,
|
| 236 |
+
"I-ZIPCODE": 89,
|
| 237 |
+
"O": 0
|
| 238 |
+
},
|
| 239 |
+
"max_position_embeddings": 512,
|
| 240 |
+
"model_type": "distilbert",
|
| 241 |
+
"n_heads": 12,
|
| 242 |
+
"n_layers": 6,
|
| 243 |
+
"pad_token_id": 0,
|
| 244 |
+
"qa_dropout": 0.1,
|
| 245 |
+
"seq_classif_dropout": 0.2,
|
| 246 |
+
"sinusoidal_pos_embds": false,
|
| 247 |
+
"tie_weights_": true,
|
| 248 |
+
"torch_dtype": "float32",
|
| 249 |
+
"transformers_version": "4.49.0",
|
| 250 |
+
"vocab_size": 30522
|
| 251 |
+
}
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2023135377e1e4f4620211d0cb7869f5b00819208392f1f3f408d71385d6943
|
| 3 |
+
size 265926088
|
onnx/model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2b779229cf73d9eba4d90bfe4405190404c65c20f06d607a50a0a367db8c9c1
|
| 3 |
+
size 119657300
|
onnx/model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c71dbd2a9a3994e606b245939889e48dc8afb7edf9a43a7c96c79727b5cf38c
|
| 3 |
+
size 133029989
|
onnx/model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6faa1d7f5b54140bbba18ba87480e11073927b5fff16f69558bd51058a05b305
|
| 3 |
+
size 67023963
|
onnx/model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a02d8c35b18f6f8eaea076c16bc0daf00bfb155b03bbc46bcf532c3d8a851d45
|
| 3 |
+
size 122316563
|
onnx/model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc101bdc8affdf2d1e8780af3db600fbe10ffc02de9edb9ce40e187d800c6a93
|
| 3 |
+
size 71866128
|
onnx/model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6faa1d7f5b54140bbba18ba87480e11073927b5fff16f69558bd51058a05b305
|
| 3 |
+
size 67023963
|
onnx/model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:629bb7348a6a32eeb7d46369b5bc73548840e6d4ccb1921adbd4437d8a745277
|
| 3 |
+
size 67023963
|
quantize_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"modes": [
|
| 3 |
+
"fp16",
|
| 4 |
+
"q8",
|
| 5 |
+
"int8",
|
| 6 |
+
"uint8",
|
| 7 |
+
"q4",
|
| 8 |
+
"q4f16",
|
| 9 |
+
"bnb4"
|
| 10 |
+
],
|
| 11 |
+
"per_channel": true,
|
| 12 |
+
"reduce_range": true,
|
| 13 |
+
"block_size": null,
|
| 14 |
+
"is_symmetric": true,
|
| 15 |
+
"accuracy_level": null,
|
| 16 |
+
"quant_type": 1,
|
| 17 |
+
"op_block_list": null
|
| 18 |
+
}
|
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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 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_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 512,
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
+
"sep_token": "[SEP]",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"strip_accents": null,
|
| 58 |
+
"tokenize_chinese_chars": true,
|
| 59 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 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
|
|
|