First version of the NER_legal_de

config.json

@@ -0,0 +1,103 @@
+{
+  "_name_or_path": "C:\\Users\\Lenovo\\PycharmProjects\\pythonProject\\Legal NER",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-AN",
+    "1": "B-EUN",
+    "2": "B-GRT",
+    "3": "B-GS",
+    "4": "B-INN",
+    "5": "B-LD",
+    "6": "B-LDS",
+    "7": "B-LIT",
+    "8": "B-MRK",
+    "9": "B-ORG",
+    "10": "B-PER",
+    "11": "B-RR",
+    "12": "B-RS",
+    "13": "B-ST",
+    "14": "B-STR",
+    "15": "B-UN",
+    "16": "B-VO",
+    "17": "B-VS",
+    "18": "B-VT",
+    "19": "I-AN",
+    "20": "I-EUN",
+    "21": "I-GRT",
+    "22": "I-GS",
+    "23": "I-INN",
+    "24": "I-LD",
+    "25": "I-LDS",
+    "26": "I-LIT",
+    "27": "I-MRK",
+    "28": "I-ORG",
+    "29": "I-PER",
+    "30": "I-RR",
+    "31": "I-RS",
+    "32": "I-ST",
+    "33": "I-STR",
+    "34": "I-UN",
+    "35": "I-VO",
+    "36": "I-VS",
+    "37": "I-VT",
+    "38": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-AN": 0,
+    "B-EUN": 1,
+    "B-GRT": 2,
+    "B-GS": 3,
+    "B-INN": 4,
+    "B-LD": 5,
+    "B-LDS": 6,
+    "B-LIT": 7,
+    "B-MRK": 8,
+    "B-ORG": 9,
+    "B-PER": 10,
+    "B-RR": 11,
+    "B-RS": 12,
+    "B-ST": 13,
+    "B-STR": 14,
+    "B-UN": 15,
+    "B-VO": 16,
+    "B-VS": 17,
+    "B-VT": 18,
+    "I-AN": 19,
+    "I-EUN": 20,
+    "I-GRT": 21,
+    "I-GS": 22,
+    "I-INN": 23,
+    "I-LD": 24,
+    "I-LDS": 25,
+    "I-LIT": 26,
+    "I-MRK": 27,
+    "I-ORG": 28,
+    "I-PER": 29,
+    "I-RR": 30,
+    "I-RS": 31,
+    "I-ST": 32,
+    "I-STR": 33,
+    "I-UN": 34,
+    "I-VO": 35,
+    "I-VS": 36,
+    "I-VT": 37,
+    "O": 38
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 31102
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc6c77cf2446106744b820538e15caf10f548d68560572622dd7e8fd4453ace
+size 1339074999

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0d552e6558801034fb902ea85427b97bbb9b4eddd16a6c931d503adf2cde7b
+size 1343618924

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "max_len": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "deepset/gbert-large"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292dc8e88e9cda03461dae5cc0446345c6f0f0ee98e335c701f2595f991287fe
+size 1775