Upload 4 files
Browse files- config.json +20 -0
- pytorch_model.bin +3 -0
- tokenizer_config.json +9 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForPreTraining"
|
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 |
+
"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 |
+
"tokenizer_class": "BertJapaneseTokenizer",
|
18 |
+
"type_vocab_size": 6,
|
19 |
+
"vocab_size": 32768
|
20 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3d35a4f6f160bb72bd59416188b0ec669bb115caa9ee8b1f9fcb24b78c72315
|
3 |
+
size 447395386
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": false,
|
3 |
+
"word_tokenizer_type": "mecab",
|
4 |
+
"subword_tokenizer_type": "wordpiece",
|
5 |
+
"mecab_kwargs": {
|
6 |
+
"normalize_text": true,
|
7 |
+
"mecab_dic": "unidic_lite"
|
8 |
+
}
|
9 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|