m

README.md

@@ -0,0 +1,5 @@
+---
+language: ar
+widget:
+  - text: 'واش هاد ال+ شي مخص ل+ دراري ال+ صغار'
+---

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "./train/checkpoint-19999",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "EG",
+    "1": "SY",
+    "2": "PL",
+    "3": "KW",
+    "4": "LB",
+    "5": "LY",
+    "6": "JO",
+    "7": "DZ",
+    "8": "QA",
+    "9": "AE",
+    "10": "BH",
+    "11": "SA",
+    "12": "OM",
+    "13": "MA",
+    "14": "IQ",
+    "15": "TN",
+    "16": "SD",
+    "17": "YE",
+    "18": "MSA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AE": 9,
+    "BH": 10,
+    "DZ": 7,
+    "EG": 0,
+    "IQ": 14,
+    "JO": 6,
+    "KW": 3,
+    "LB": 4,
+    "LY": 5,
+    "MA": 13,
+    "MSA": 18,
+    "OM": 12,
+    "PL": 2,
+    "QA": 8,
+    "SA": 11,
+    "SD": 16,
+    "SY": 1,
+    "TN": 15,
+    "YE": 17
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf175ca1a99018a59a1f0d3c5d7922427e55de745e2e198299159649377348eb
+size 651494829

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "UBC-NLP/ARBERT",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669cb8fcfa1839329c27d29aaad547da14dad9e581cdec97103185c9b8ce99c2
+size 3247