Training in progress epoch 0
Browse files- README.md +54 -0
- config.json +30 -0
- special_tokens_map.json +37 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +339 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabert
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_keras_callback
|
| 6 |
+
model-index:
|
| 7 |
+
- name: I042/bert-base-arabert-finetuned-wikitext2
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 12 |
+
probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# I042/bert-base-arabert-finetuned-wikitext2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabert](https://huggingface.co/aubmindlab/bert-base-arabert) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 3.5692
|
| 19 |
+
- Validation Loss: 3.0649
|
| 20 |
+
- Epoch: 0
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
| 40 |
+
- training_precision: float32
|
| 41 |
+
|
| 42 |
+
### Training results
|
| 43 |
+
|
| 44 |
+
| Train Loss | Validation Loss | Epoch |
|
| 45 |
+
|:----------:|:---------------:|:-----:|
|
| 46 |
+
| 3.5692 | 3.0649 | 0 |
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
### Framework versions
|
| 50 |
+
|
| 51 |
+
- Transformers 4.44.2
|
| 52 |
+
- TensorFlow 2.17.0
|
| 53 |
+
- Datasets 3.0.0
|
| 54 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aubmindlab/bert-base-arabert",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_fc_size": 768,
|
| 21 |
+
"pooler_num_attention_heads": 12,
|
| 22 |
+
"pooler_num_fc_layers": 3,
|
| 23 |
+
"pooler_size_per_head": 128,
|
| 24 |
+
"pooler_type": "first_token_transform",
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"transformers_version": "4.44.2",
|
| 27 |
+
"type_vocab_size": 2,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 64000
|
| 30 |
+
}
|
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 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ed42a13d2b6048afcb09a92262728d74dad6c9da9982b4a8d92e218b550c2e5
|
| 3 |
+
size 739510360
|
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 |
+
"124": {
|
| 4 |
+
"content": "+ุง",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": true,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"125": {
|
| 12 |
+
"content": "+ุฉ",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": true,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"126": {
|
| 20 |
+
"content": "+ุช",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": true,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"127": {
|
| 28 |
+
"content": "+ู",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": true,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128": {
|
| 36 |
+
"content": "+ู",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": true,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"129": {
|
| 44 |
+
"content": "+ู",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": true,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"130": {
|
| 52 |
+
"content": "+ู",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": true,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"448": {
|
| 60 |
+
"content": "ุจ+",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": true,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"635": {
|
| 68 |
+
"content": "ุณ+",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": true,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"765": {
|
| 76 |
+
"content": "ู+",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": true,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"802": {
|
| 84 |
+
"content": "ู+",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": true,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"816": {
|
| 92 |
+
"content": "ู+",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": true,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"897": {
|
| 100 |
+
"content": "ู+",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": true,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"1012": {
|
| 108 |
+
"content": "+ุงุช",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": true,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"1013": {
|
| 116 |
+
"content": "+ุงู",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": true,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"1015": {
|
| 124 |
+
"content": "+ูู
",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": true,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"1016": {
|
| 132 |
+
"content": "+ูู",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": true,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"1017": {
|
| 140 |
+
"content": "+ูุง",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": true,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"1018": {
|
| 148 |
+
"content": "+ูุง",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": true,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"1019": {
|
| 156 |
+
"content": "+ูู
",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": true,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"1020": {
|
| 164 |
+
"content": "+ูู",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": true,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"1021": {
|
| 172 |
+
"content": "+ูุง",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": true,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"1022": {
|
| 180 |
+
"content": "+ูู",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": true,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"1023": {
|
| 188 |
+
"content": "+ูู",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": true,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"3000": {
|
| 196 |
+
"content": "ุงู+",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": true,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"6154": {
|
| 204 |
+
"content": "ูู+",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": true,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"8270": {
|
| 212 |
+
"content": "+ูู
ุง",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": true,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"8271": {
|
| 220 |
+
"content": "+ูู
ุง",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": true,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"29756": {
|
| 228 |
+
"content": "[CLS]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"29757": {
|
| 236 |
+
"content": "[PAD]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"29758": {
|
| 244 |
+
"content": "[SEP]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"29759": {
|
| 252 |
+
"content": "[UNK]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"46585": {
|
| 260 |
+
"content": "[MASK]",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"46586": {
|
| 268 |
+
"content": "[ุจุฑูุฏ]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": true,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"46587": {
|
| 276 |
+
"content": "[ุฑุงุจุท]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": true,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"57701": {
|
| 284 |
+
"content": "[ู
ุณุชุฎุฏู
]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": true,
|
| 289 |
+
"special": true
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"clean_up_tokenization_spaces": true,
|
| 293 |
+
"cls_token": "[CLS]",
|
| 294 |
+
"do_basic_tokenize": true,
|
| 295 |
+
"do_lower_case": false,
|
| 296 |
+
"full_tokenizer_file": null,
|
| 297 |
+
"mask_token": "[MASK]",
|
| 298 |
+
"max_len": 512,
|
| 299 |
+
"model_max_length": 512,
|
| 300 |
+
"never_split": [
|
| 301 |
+
"+ูุง",
|
| 302 |
+
"ุณ+",
|
| 303 |
+
"[ู
ุณุชุฎุฏู
]",
|
| 304 |
+
"+ู",
|
| 305 |
+
"+ูู
",
|
| 306 |
+
"+ุฉ",
|
| 307 |
+
"+ู",
|
| 308 |
+
"ูู+",
|
| 309 |
+
"[ุจุฑูุฏ]",
|
| 310 |
+
"[ุฑุงุจุท]",
|
| 311 |
+
"+ู",
|
| 312 |
+
"+ูู",
|
| 313 |
+
"+ุง",
|
| 314 |
+
"+ุงุช",
|
| 315 |
+
"+ู",
|
| 316 |
+
"ุจ+",
|
| 317 |
+
"+ูุง",
|
| 318 |
+
"+ูู",
|
| 319 |
+
"+ูู
",
|
| 320 |
+
"ู+",
|
| 321 |
+
"+ูู",
|
| 322 |
+
"+ูู
ุง",
|
| 323 |
+
"ู+",
|
| 324 |
+
"+ูู
ุง",
|
| 325 |
+
"+ุงู",
|
| 326 |
+
"+ุช",
|
| 327 |
+
"+ูู",
|
| 328 |
+
"ู+",
|
| 329 |
+
"+ูุง",
|
| 330 |
+
"ุงู+",
|
| 331 |
+
"ู+"
|
| 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
|
|
|