Add ko-mbertmodel-monotok-adapter
Browse files- config.json +64 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"adapters": {
|
3 |
+
"adapters": {
|
4 |
+
},
|
5 |
+
"config_map": {
|
6 |
+
"d345095bcb01e325": {
|
7 |
+
"adapter_residual_before_ln": false,
|
8 |
+
"attention_type": null,
|
9 |
+
"invertible_adapter": null,
|
10 |
+
"leave_out": [],
|
11 |
+
"ln_after": false,
|
12 |
+
"ln_before": false,
|
13 |
+
"mh_adapter": false,
|
14 |
+
"new_attention_norm": null,
|
15 |
+
"non_linearity": "gelu",
|
16 |
+
"original_ln_after": true,
|
17 |
+
"original_ln_before": true,
|
18 |
+
"output_adapter": true,
|
19 |
+
"reduction_factor": 2,
|
20 |
+
"residual_before_ln": true
|
21 |
+
},
|
22 |
+
"text_lang": {
|
23 |
+
"adapter_residual_before_ln": false,
|
24 |
+
"attention_type": null,
|
25 |
+
"invertible_adapter": null,
|
26 |
+
"leave_out": [],
|
27 |
+
"ln_after": false,
|
28 |
+
"ln_before": false,
|
29 |
+
"mh_adapter": false,
|
30 |
+
"new_attention_norm": null,
|
31 |
+
"non_linearity": "gelu",
|
32 |
+
"original_ln_after": true,
|
33 |
+
"original_ln_before": true,
|
34 |
+
"output_adapter": true,
|
35 |
+
"reduction_factor": 2,
|
36 |
+
"residual_before_ln": true
|
37 |
+
}
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"architectures": [
|
41 |
+
"BertForMaskedLM"
|
42 |
+
],
|
43 |
+
"attention_probs_dropout_prob": 0.1,
|
44 |
+
"directionality": "bidi",
|
45 |
+
"embeddings_type": "full",
|
46 |
+
"hidden_act": "gelu",
|
47 |
+
"hidden_dropout_prob": 0.1,
|
48 |
+
"hidden_size": 768,
|
49 |
+
"initializer_range": 0.02,
|
50 |
+
"intermediate_size": 3072,
|
51 |
+
"layer_norm_eps": 1e-12,
|
52 |
+
"max_position_embeddings": 512,
|
53 |
+
"model_type": "bert",
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_hidden_layers": 12,
|
56 |
+
"pad_token_id": 0,
|
57 |
+
"pooler_fc_size": 768,
|
58 |
+
"pooler_num_attention_heads": 12,
|
59 |
+
"pooler_num_fc_layers": 3,
|
60 |
+
"pooler_size_per_head": 128,
|
61 |
+
"pooler_type": "first_token_transform",
|
62 |
+
"type_vocab_size": 2,
|
63 |
+
"vocab_size": 16424
|
64 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eb66e62d8a2069c0d1c7c60bdf7632e14cb2e01a87ee07c453214811364595b
|
3 |
+
size 425535903
|
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_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "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, "max_len": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "hgiyt/ko-mbertmodel-monotok-adapter"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|