Add files using upload-large-folder tool

.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 +1,115 @@
+{
+  "_name_or_path": "joeranbosma/dragon-roberta-large-mixed-domain",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-<ACCREDATIE_NUMMER>",
+    "1": "B-<ADRES>",
+    "2": "B-<AGBNUMMER>",
+    "3": "B-<BEDRIJF>",
+    "4": "B-<BIGNUMMER>",
+    "5": "B-<BSN>",
+    "6": "B-<DATUM>",
+    "7": "B-<DOCUMENTID>",
+    "8": "B-<DOCUMENTNUMMER>",
+    "9": "B-<EMAIL>",
+    "10": "B-<IBAN>",
+    "11": "B-<LEEFTIJD>",
+    "12": "B-<PATIENTNUMMER>",
+    "13": "B-<PERSOON>",
+    "14": "B-<PERSOONAFKORTING>",
+    "15": "B-<PHINUMMER>",
+    "16": "B-<PLAATS>",
+    "17": "B-<RAPPORT_ID>",
+    "18": "B-<STUDIE_NAAM>",
+    "19": "B-<TELEFOONNUMMER>",
+    "20": "B-<TIJD>",
+    "21": "B-<URL>",
+    "22": "B-<ZIEKENHUIS>",
+    "23": "I-<ACCREDATIE_NUMMER>",
+    "24": "I-<ADRES>",
+    "25": "I-<BEDRIJF>",
+    "26": "I-<DATUM>",
+    "27": "I-<EMAIL>",
+    "28": "I-<IBAN>",
+    "29": "I-<LEEFTIJD>",
+    "30": "I-<PERSOON>",
+    "31": "I-<PERSOONAFKORTING>",
+    "32": "I-<PHINUMMER>",
+    "33": "I-<PLAATS>",
+    "34": "I-<RAPPORT_ID>",
+    "35": "I-<STUDIE_NAAM>",
+    "36": "I-<TELEFOONNUMMER>",
+    "37": "I-<TIJD>",
+    "38": "I-<URL>",
+    "39": "I-<ZIEKENHUIS>",
+    "40": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-<ACCREDATIE_NUMMER>": 0,
+    "B-<ADRES>": 1,
+    "B-<AGBNUMMER>": 2,
+    "B-<BEDRIJF>": 3,
+    "B-<BIGNUMMER>": 4,
+    "B-<BSN>": 5,
+    "B-<DATUM>": 6,
+    "B-<DOCUMENTID>": 7,
+    "B-<DOCUMENTNUMMER>": 8,
+    "B-<EMAIL>": 9,
+    "B-<IBAN>": 10,
+    "B-<LEEFTIJD>": 11,
+    "B-<PATIENTNUMMER>": 12,
+    "B-<PERSOON>": 13,
+    "B-<PERSOONAFKORTING>": 14,
+    "B-<PHINUMMER>": 15,
+    "B-<PLAATS>": 16,
+    "B-<RAPPORT_ID>": 17,
+    "B-<STUDIE_NAAM>": 18,
+    "B-<TELEFOONNUMMER>": 19,
+    "B-<TIJD>": 20,
+    "B-<URL>": 21,
+    "B-<ZIEKENHUIS>": 22,
+    "I-<ACCREDATIE_NUMMER>": 23,
+    "I-<ADRES>": 24,
+    "I-<BEDRIJF>": 25,
+    "I-<DATUM>": 26,
+    "I-<EMAIL>": 27,
+    "I-<IBAN>": 28,
+    "I-<LEEFTIJD>": 29,
+    "I-<PERSOON>": 30,
+    "I-<PERSOONAFKORTING>": 31,
+    "I-<PHINUMMER>": 32,
+    "I-<PLAATS>": 33,
+    "I-<RAPPORT_ID>": 34,
+    "I-<STUDIE_NAAM>": 35,
+    "I-<TELEFOONNUMMER>": 36,
+    "I-<TIJD>": 37,
+    "I-<URL>": 38,
+    "I-<ZIEKENHUIS>": 39,
+    "O": 40
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c2816523f0efeac7cbedc8c19f9ead788d5196de065928659fdfc4b7488141
+size 2235579964

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d58f087716f5709e4da76c5be127f3b1b10e6a793b64c6d49eadd879e52ccc
+size 17082785

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181ecc71f9d7dac8ed19af6c0a55c36863f8fc2e7039deb71a646fc00fa21e45
+size 4219