Upload 9 files

README.md

@@ -0,0 +1,29 @@
+---
+license: cc-by-nc-sa-4.0
+language:
+- he
+metrics:
+- accuracy
+pipeline_tag: text-classification
+tags:
+- code
+---
+
+## Hebrew Corpus
+
+This corpus contains offensive language in Hebrew manually annotated. The data includes 15,881 tweets, labeled with one or more of five classes (abusive, hate, violence, pornographic, or non-offensive). The corpus is annonated manually by Arabic-Hebrew bilingual speakers.
+
+https://arxiv.org/abs/2309.02724
+
+## Models
+
+AlephBERT (https://huggingface.co/imvladikon/sentence-transformers-alephbert) 
+
+
+## Github Repository
+
+git clone https://github.com/SinaLab/OffensiveHebrew
+
+You can download the data from the following GitGub link:
+
+https://github.com/SinaLab/OffensiveHebrew/tree/main/data

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "onlplab/alephbert-base",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.27.4",
+    "pytorch": "2.0.0+cu118"
+  }
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

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 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "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]"
+}