naghamghanim
commited on
Commit
โข
e56d95e
1
Parent(s):
a05ef74
Upload 5 files
Browse files- config.json +17 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"hidden_act": "gelu",
|
7 |
+
"hidden_dropout_prob": 0.1,
|
8 |
+
"hidden_size": 768,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 3072,
|
11 |
+
"max_position_embeddings": 512,
|
12 |
+
"model_type": "bert",
|
13 |
+
"num_attention_heads": 12,
|
14 |
+
"num_hidden_layers": 12,
|
15 |
+
"type_vocab_size": 2,
|
16 |
+
"vocab_size": 64000
|
17 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "max_len": 512, "do_basic_tokenize": true, "never_split": ["+ู", "+ูู
ุง", "ู+", "+ูุง", "+ูู", "ู+", "+ูู", "+ุงู", "+ูู
", "+ุฉ", "[ุจุฑูุฏ]", "ูู+", "+ู", "+ุช", "+ู", "ุณ+", "ู+", "[ู
ุณุชุฎุฏู
]", "+ูู
", "+ุง", "ุจ+", "ู+", "+ูุง", "+ูุง", "+ูู", "+ูู
ุง", "ุงู+", "+ู", "+ูู", "+ุงุช", "[ุฑุงุจุท]"], "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-large-arabertv2"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|