Commit
•
7415669
1
Parent(s):
dd97995
Training in progress, step 500
Browse files- config.json +25 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +48 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.33.1",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 64000
|
| 25 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fc2b39a3e12c5b4f994d131519f0122e231f9703d1ea66db89f00d27a138108
|
| 3 |
+
size 538484905
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"max_len": 512,
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"never_split": [
|
| 10 |
+
"+ك",
|
| 11 |
+
"+كما",
|
| 12 |
+
"ك+",
|
| 13 |
+
"+وا",
|
| 14 |
+
"+ين",
|
| 15 |
+
"و+",
|
| 16 |
+
"+كن",
|
| 17 |
+
"+ان",
|
| 18 |
+
"+هم",
|
| 19 |
+
"+ة",
|
| 20 |
+
"[بريد]",
|
| 21 |
+
"لل+",
|
| 22 |
+
"+ي",
|
| 23 |
+
"+ت",
|
| 24 |
+
"+ن",
|
| 25 |
+
"س+",
|
| 26 |
+
"ل+",
|
| 27 |
+
"[مستخدم]",
|
| 28 |
+
"+كم",
|
| 29 |
+
"+ا",
|
| 30 |
+
"ب+",
|
| 31 |
+
"ف+",
|
| 32 |
+
"+نا",
|
| 33 |
+
"+ها",
|
| 34 |
+
"+ون",
|
| 35 |
+
"+هما",
|
| 36 |
+
"ال+",
|
| 37 |
+
"+ه",
|
| 38 |
+
"+هن",
|
| 39 |
+
"+ات",
|
| 40 |
+
"[رابط]"
|
| 41 |
+
],
|
| 42 |
+
"pad_token": "[PAD]",
|
| 43 |
+
"sep_token": "[SEP]",
|
| 44 |
+
"strip_accents": null,
|
| 45 |
+
"tokenize_chinese_chars": true,
|
| 46 |
+
"tokenizer_class": "BertTokenizer",
|
| 47 |
+
"unk_token": "[UNK]"
|
| 48 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f45dc65b0d16ff09079557385dcd9fd007010a15fd68baf2f905fc3ddeb0958
|
| 3 |
+
size 4027
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|