deeqBERT-base
Browse files- README.md +14 -0
- config.json +23 -0
- pytorch_model.bin +3 -0
- tokenizer_config.json +4 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: ko
|
| 3 |
+
datasets:
|
| 4 |
+
- kowiki
|
| 5 |
+
- news
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
deeqBERT-base
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
- model: bert-base
|
| 12 |
+
- vocab: bert-wordpiece, 35k
|
| 13 |
+
- version: latest
|
| 14 |
+
|
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"model_type": "bert",
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"num_attention_heads": 12,
|
| 15 |
+
"num_hidden_layers": 12,
|
| 16 |
+
"pooler_fc_size": 768,
|
| 17 |
+
"pooler_num_attention_heads": 12,
|
| 18 |
+
"pooler_num_fc_layers": 3,
|
| 19 |
+
"pooler_size_per_head": 128,
|
| 20 |
+
"pooler_type": "first_token_transform",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"vocab_size": 35000
|
| 23 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef853d4b03ed00667b502ccc67267ced33a6997fb704f554c4c82097157acffa
|
| 3 |
+
size 454288758
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_lower_case": false,
|
| 3 |
+
"model_max_length": 128
|
| 4 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|