Upload 6 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,101 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-AGE",
+    "1": "B-BUILDINGNUM",
+    "2": "B-CITY",
+    "3": "B-CREDITCARDNUMBER",
+    "4": "B-DATE",
+    "5": "B-DRIVERLICENSENUM",
+    "6": "B-EMAIL",
+    "7": "B-GENDER",
+    "8": "B-GIVENNAME",
+    "9": "B-IDCARDNUM",
+    "10": "B-PASSPORTNUM",
+    "11": "B-SEX",
+    "12": "B-SOCIALNUM",
+    "13": "B-STREET",
+    "14": "B-SURNAME",
+    "15": "B-TAXNUM",
+    "16": "B-TELEPHONENUM",
+    "17": "B-TIME",
+    "18": "B-TITLE",
+    "19": "B-ZIPCODE",
+    "20": "I-BUILDINGNUM",
+    "21": "I-CITY",
+    "22": "I-DATE",
+    "23": "I-DRIVERLICENSENUM",
+    "24": "I-EMAIL",
+    "25": "I-GIVENNAME",
+    "26": "I-SOCIALNUM",
+    "27": "I-STREET",
+    "28": "I-SURNAME",
+    "29": "I-TAXNUM",
+    "30": "I-TELEPHONENUM",
+    "31": "I-TIME",
+    "32": "I-TITLE",
+    "33": "I-ZIPCODE",
+    "34": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGE": 0,
+    "B-BUILDINGNUM": 1,
+    "B-CITY": 2,
+    "B-CREDITCARDNUMBER": 3,
+    "B-DATE": 4,
+    "B-DRIVERLICENSENUM": 5,
+    "B-EMAIL": 6,
+    "B-GENDER": 7,
+    "B-GIVENNAME": 8,
+    "B-IDCARDNUM": 9,
+    "B-PASSPORTNUM": 10,
+    "B-SEX": 11,
+    "B-SOCIALNUM": 12,
+    "B-STREET": 13,
+    "B-SURNAME": 14,
+    "B-TAXNUM": 15,
+    "B-TELEPHONENUM": 16,
+    "B-TIME": 17,
+    "B-TITLE": 18,
+    "B-ZIPCODE": 19,
+    "I-BUILDINGNUM": 20,
+    "I-CITY": 21,
+    "I-DATE": 22,
+    "I-DRIVERLICENSENUM": 23,
+    "I-EMAIL": 24,
+    "I-GIVENNAME": 25,
+    "I-SOCIALNUM": 26,
+    "I-STREET": 27,
+    "I-SURNAME": 28,
+    "I-TAXNUM": 29,
+    "I-TELEPHONENUM": 30,
+    "I-TIME": 31,
+    "I-TITLE": 32,
+    "I-ZIPCODE": 33,
+    "O": 34
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e63047250175a9aef7c09977fc2de23555bccb2c85d644eee8289dd70c5b176
+size 278253293

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}