Upload Arabic BERT hate speech detection model
Browse files- README.md +94 -0
- config.json +25 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +339 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: ar
|
| 3 |
+
license: mit
|
| 4 |
+
tags:
|
| 5 |
+
- arabic
|
| 6 |
+
- hate-speech-detection
|
| 7 |
+
- bert
|
| 8 |
+
- text-classification
|
| 9 |
+
- pytorch
|
| 10 |
+
datasets:
|
| 11 |
+
- arabic-levantine-hate-speech-detection
|
| 12 |
+
metrics:
|
| 13 |
+
- accuracy
|
| 14 |
+
- f1
|
| 15 |
+
model-index:
|
| 16 |
+
- name: arabic-bert-hate-speech-detection
|
| 17 |
+
results:
|
| 18 |
+
- task:
|
| 19 |
+
type: text-classification
|
| 20 |
+
name: Hate Speech Detection
|
| 21 |
+
dataset:
|
| 22 |
+
type: arabic-levantine-hate-speech-detection
|
| 23 |
+
name: Arabic Levantine Hate Speech Detection
|
| 24 |
+
metrics:
|
| 25 |
+
- type: accuracy
|
| 26 |
+
value: 0.845
|
| 27 |
+
name: Accuracy
|
| 28 |
+
- type: f1
|
| 29 |
+
value: 0.84
|
| 30 |
+
name: F1 Score
|
| 31 |
+
---
|
| 32 |
+
|
| 33 |
+
# Arabic BERT Hate Speech Detection
|
| 34 |
+
|
| 35 |
+
This model is a fine-tuned version of `aubmindlab/bert-base-arabertv2` for Arabic hate speech detection.
|
| 36 |
+
|
| 37 |
+
## Model Description
|
| 38 |
+
|
| 39 |
+
- **Base Model**: aubmindlab/bert-base-arabertv2
|
| 40 |
+
- **Task**: Binary text classification (Normal vs Hate Speech)
|
| 41 |
+
- **Language**: Arabic
|
| 42 |
+
- **Accuracy**: 84.5%
|
| 43 |
+
|
| 44 |
+
## Usage
|
| 45 |
+
|
| 46 |
+
```python
|
| 47 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 48 |
+
import torch
|
| 49 |
+
|
| 50 |
+
# Load model and tokenizer
|
| 51 |
+
model_name = "Ibracadabra13/arabic-bert-hate-speech-detection"
|
| 52 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 53 |
+
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
| 54 |
+
|
| 55 |
+
# Function to predict hate speech
|
| 56 |
+
def predict_hate_speech(text):
|
| 57 |
+
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
|
| 58 |
+
|
| 59 |
+
with torch.no_grad():
|
| 60 |
+
outputs = model(**inputs)
|
| 61 |
+
predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
|
| 62 |
+
predicted_class = torch.argmax(predictions, dim=-1).item()
|
| 63 |
+
confidence = predictions[0][predicted_class].item()
|
| 64 |
+
|
| 65 |
+
label_map = {0: 'Normal', 1: 'Hate Speech'}
|
| 66 |
+
return {
|
| 67 |
+
'prediction': label_map[predicted_class],
|
| 68 |
+
'confidence': confidence,
|
| 69 |
+
'is_hate_speech': predicted_class == 1
|
| 70 |
+
}
|
| 71 |
+
|
| 72 |
+
# Example usage
|
| 73 |
+
result = predict_hate_speech("أنت حيوان حقير")
|
| 74 |
+
print(result) # {'prediction': 'Hate Speech', 'confidence': 0.97, 'is_hate_speech': True}
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
## Training Details
|
| 78 |
+
|
| 79 |
+
- **Training Data**: Arabic Levantine Hate Speech Detection Dataset
|
| 80 |
+
- **Training Method**: Fine-tuning with manual training loop
|
| 81 |
+
- **Epochs**: 2
|
| 82 |
+
- **Batch Size**: 4
|
| 83 |
+
- **Learning Rate**: 2e-5
|
| 84 |
+
- **Optimizer**: AdamW
|
| 85 |
+
|
| 86 |
+
## Performance
|
| 87 |
+
|
| 88 |
+
- **Accuracy**: 84.5%
|
| 89 |
+
- **Normal Text**: 83% precision, 96% recall
|
| 90 |
+
- **Hate Speech**: 90% precision, 65% recall
|
| 91 |
+
|
| 92 |
+
## Limitations
|
| 93 |
+
|
| 94 |
+
This model is trained on a specific dataset and may not generalize well to all Arabic dialects or contexts. Use with caution in production environments.
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "bert",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"position_embedding_type": "absolute",
|
| 19 |
+
"problem_type": "single_label_classification",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.53.3",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 64000
|
| 25 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62c161a1086009402c70a0662e53b806e32d22fa77c3a988830c76923c1173ee
|
| 3 |
+
size 540803072
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "+ا",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": true,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "+ك",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": true,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "ب+",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": true,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "+هم",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": true,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "+ات",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": true,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "+ي",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": true,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "ل+",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": true,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "+هما",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": true,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "+نا",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": true,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"9": {
|
| 76 |
+
"content": "+ن",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": true,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"10": {
|
| 84 |
+
"content": "+ها",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": true,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"11": {
|
| 92 |
+
"content": "+كما",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": true,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"12": {
|
| 100 |
+
"content": "+ة",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": true,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"13": {
|
| 108 |
+
"content": "ف+",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": true,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"14": {
|
| 116 |
+
"content": "+كم",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": true,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"15": {
|
| 124 |
+
"content": "+كن",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": true,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"16": {
|
| 132 |
+
"content": "+ت",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": true,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"17": {
|
| 140 |
+
"content": "[بريد]",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": true,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"18": {
|
| 148 |
+
"content": "[مستخدم]",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": true,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"19": {
|
| 156 |
+
"content": "لل+",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": true,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"20": {
|
| 164 |
+
"content": "ال+",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": true,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"21": {
|
| 172 |
+
"content": "[رابط]",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": true,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"22": {
|
| 180 |
+
"content": "س+",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": true,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"23": {
|
| 188 |
+
"content": "+ان",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": true,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"24": {
|
| 196 |
+
"content": "+وا",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": true,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"25": {
|
| 204 |
+
"content": "+ه",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": true,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"26": {
|
| 212 |
+
"content": "+ون",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": true,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"27": {
|
| 220 |
+
"content": "+هن",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": true,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"28": {
|
| 228 |
+
"content": "+ين",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": true,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"29": {
|
| 236 |
+
"content": "��+",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": true,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"30": {
|
| 244 |
+
"content": "ك+",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": true,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": true,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"31": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32": {
|
| 260 |
+
"content": "[UNK]",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"33": {
|
| 268 |
+
"content": "[CLS]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"34": {
|
| 276 |
+
"content": "[SEP]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"35": {
|
| 284 |
+
"content": "[MASK]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"clean_up_tokenization_spaces": false,
|
| 293 |
+
"cls_token": "[CLS]",
|
| 294 |
+
"do_basic_tokenize": true,
|
| 295 |
+
"do_lower_case": false,
|
| 296 |
+
"extra_special_tokens": {},
|
| 297 |
+
"mask_token": "[MASK]",
|
| 298 |
+
"max_len": 512,
|
| 299 |
+
"model_max_length": 512,
|
| 300 |
+
"never_split": [
|
| 301 |
+
"+ك",
|
| 302 |
+
"+كما",
|
| 303 |
+
"ك+",
|
| 304 |
+
"+وا",
|
| 305 |
+
"+ين",
|
| 306 |
+
"و+",
|
| 307 |
+
"+كن",
|
| 308 |
+
"+ان",
|
| 309 |
+
"+هم",
|
| 310 |
+
"+ة",
|
| 311 |
+
"[بريد]",
|
| 312 |
+
"لل+",
|
| 313 |
+
"+ي",
|
| 314 |
+
"+ت",
|
| 315 |
+
"+ن",
|
| 316 |
+
"س+",
|
| 317 |
+
"ل+",
|
| 318 |
+
"[مستخدم]",
|
| 319 |
+
"+كم",
|
| 320 |
+
"+ا",
|
| 321 |
+
"ب+",
|
| 322 |
+
"ف+",
|
| 323 |
+
"+نا",
|
| 324 |
+
"+ها",
|
| 325 |
+
"+ون",
|
| 326 |
+
"+هما",
|
| 327 |
+
"ال+",
|
| 328 |
+
"+ه",
|
| 329 |
+
"+هن",
|
| 330 |
+
"+ات",
|
| 331 |
+
"[رابط]"
|
| 332 |
+
],
|
| 333 |
+
"pad_token": "[PAD]",
|
| 334 |
+
"sep_token": "[SEP]",
|
| 335 |
+
"strip_accents": null,
|
| 336 |
+
"tokenize_chinese_chars": true,
|
| 337 |
+
"tokenizer_class": "BertTokenizer",
|
| 338 |
+
"unk_token": "[UNK]"
|
| 339 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|