trituenhantaoio
commited on
Commit
•
63eb3f8
1
Parent(s):
9cc13a9
First version of the bert-base-vietnamese-diacritics-uncased model and tokenizer.
Browse files- config.json +27 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/Colab_data/2021/vietnamese-bert-diacritics-preserved/vietnamese-bert-diacritics-preserved/bert_model/pytorch_model",
|
3 |
+
"attention_probs_dropout_prob": 0.1,
|
4 |
+
"directionality": "bidi",
|
5 |
+
"gradient_checkpointing": false,
|
6 |
+
"hidden_act": "gelu",
|
7 |
+
"hidden_dropout_prob": 0.1,
|
8 |
+
"hidden_size": 768,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 3072,
|
11 |
+
"layer_norm_eps": 1e-12,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "bert",
|
14 |
+
"num_attention_heads": 12,
|
15 |
+
"num_hidden_layers": 12,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"pooler_fc_size": 768,
|
18 |
+
"pooler_num_attention_heads": 12,
|
19 |
+
"pooler_num_fc_layers": 3,
|
20 |
+
"pooler_size_per_head": 128,
|
21 |
+
"pooler_type": "first_token_transform",
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"transformers_version": "4.3.3",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d460de68b1d17f331c9c461b63037a33923556c0de61aaa2f351bd5d446c85a7
|
3 |
+
size 442553143
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e5807ff1dced2a6e6ff96a657d889e493743fc80e31f48196f80a4e524fc6dc
|
3 |
+
size 442731288
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|