Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

added_tokens.json +3 -0
config.json +141 -0
pytorch_model.bin +3 -0
special_tokens_map.json +15 -0
spm.model +3 -0
tokenizer.json +0 -0
tokenizer_config.json +60 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,3 @@

+{
+  "[MASK]": 128000
+}

config.json ADDED Viewed

	@@ -0,0 +1,141 @@

+{
+  "architectures": [
+    "DebertaNativeSpanClassifier"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "ACCOUNTNAME",
+    "2": "ACCOUNTNUMBER",
+    "3": "AGE",
+    "4": "AMOUNT",
+    "5": "BIC",
+    "6": "BITCOINADDRESS",
+    "7": "BUILDINGNUMBER",
+    "8": "CITY",
+    "9": "COMPANYNAME",
+    "10": "COUNTY",
+    "11": "CREDITCARDCVV",
+    "12": "CREDITCARDISSUER",
+    "13": "CREDITCARDNUMBER",
+    "14": "DATE",
+    "15": "DOB",
+    "16": "DRIVERLICENSENUM",
+    "17": "EMAIL",
+    "18": "ETHEREUMADDRESS",
+    "19": "EYECOLOR",
+    "20": "FIRSTNAME",
+    "21": "GENDER",
+    "22": "HEIGHT",
+    "23": "IBAN",
+    "24": "IPADDRESS",
+    "25": "JOBAREA",
+    "26": "JOBTYPE",
+    "27": "LASTNAME",
+    "28": "LITECOINADDRESS",
+    "29": "MASKEDNUMBER",
+    "30": "MIDDLENAME",
+    "31": "NEARBYGPSCOORDINATE",
+    "32": "ORDINALDIRECTION",
+    "33": "PASSPORTNUM",
+    "34": "PASSWORD",
+    "35": "PHONEIMEI",
+    "36": "PHONENUMBER",
+    "37": "PIN",
+    "38": "PREFIX",
+    "39": "SECONDARYADDRESS",
+    "40": "SSN/CCCD",
+    "41": "STATE",
+    "42": "STREET",
+    "43": "TAXNUM",
+    "44": "TIME",
+    "45": "URL",
+    "46": "USERAGENT",
+    "47": "USERNAME",
+    "48": "VEHICLEVIN",
+    "49": "VEHICLEVRM",
+    "50": "ZIPCODE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ACCOUNTNAME": 1,
+    "ACCOUNTNUMBER": 2,
+    "AGE": 3,
+    "AMOUNT": 4,
+    "BIC": 5,
+    "BITCOINADDRESS": 6,
+    "BUILDINGNUMBER": 7,
+    "CITY": 8,
+    "COMPANYNAME": 9,
+    "COUNTY": 10,
+    "CREDITCARDCVV": 11,
+    "CREDITCARDISSUER": 12,
+    "CREDITCARDNUMBER": 13,
+    "DATE": 14,
+    "DOB": 15,
+    "DRIVERLICENSENUM": 16,
+    "EMAIL": 17,
+    "ETHEREUMADDRESS": 18,
+    "EYECOLOR": 19,
+    "FIRSTNAME": 20,
+    "GENDER": 21,
+    "HEIGHT": 22,
+    "IBAN": 23,
+    "IPADDRESS": 24,
+    "JOBAREA": 25,
+    "JOBTYPE": 26,
+    "LASTNAME": 27,
+    "LITECOINADDRESS": 28,
+    "MASKEDNUMBER": 29,
+    "MIDDLENAME": 30,
+    "NEARBYGPSCOORDINATE": 31,
+    "O": 0,
+    "ORDINALDIRECTION": 32,
+    "PASSPORTNUM": 33,
+    "PASSWORD": 34,
+    "PHONEIMEI": 35,
+    "PHONENUMBER": 36,
+    "PIN": 37,
+    "PREFIX": 38,
+    "SECONDARYADDRESS": 39,
+    "SSN/CCCD": 40,
+    "STATE": 41,
+    "STREET": 42,
+    "TAXNUM": 43,
+    "TIME": 44,
+    "URL": 45,
+    "USERAGENT": 46,
+    "USERNAME": 47,
+    "VEHICLEVIN": 48,
+    "VEHICLEVRM": 49,
+    "ZIPCODE": 50
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ec50d993572f9db3351ce8ee1afc8b0f83f0be2beef73f7a46fa446adb7e22e2
+size 735725251

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,60 @@

+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}