First model version

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "arabic-ner-ace-gigabert/",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-VEH",
+    "4": "I-VEH",
+    "5": "B-GPE",
+    "6": "I-GPE",
+    "7": "B-WEA",
+    "8": "I-WEA",
+    "9": "B-ORG",
+    "10": "I-ORG",
+    "11": "B-LOC",
+    "12": "I-LOC",
+    "13": "B-FAC",
+    "14": "I-FAC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-FAC": 13,
+    "B-GPE": 5,
+    "B-LOC": 11,
+    "B-ORG": 9,
+    "B-PER": 1,
+    "B-VEH": 3,
+    "B-WEA": 7,
+    "I-FAC": 14,
+    "I-GPE": 6,
+    "I-LOC": 12,
+    "I-ORG": 10,
+    "I-PER": 2,
+    "I-VEH": 4,
+    "I-WEA": 8,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ac9cf454cd16e5cb43698cd1c6e7d0cc101a2c6bd8098cb8a73ce2ab102ad9
+size 495519537

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6893c16bc620c4e698e08dd0b47a114ec9cca96ca63c378ee114824ea7bbee
+size 498082204

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "lanwuwei/GigaBERT-v4-Arabic-and-English",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/srv/share5/ychen3411/huggingface_cache/c8a919731ad7551df88a744a8399190ea80a9961eaf96b8a59f86ef617e5144f.6a644b330fad284f98393c5832f71bce43df6855fa6ac7c9e44ed6271b708170",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}