Commit
•
e4a209d
1
Parent(s):
0579dcd
Upload folder using huggingface_hub
Browse files- config.json +61 -0
- mlm_vocab.txt +0 -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 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "helboukkouri/character-bert",
|
3 |
+
"architectures": [
|
4 |
+
"CharacterBertForPreTraining"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "configuration_character_bert.CharacterBertConfig",
|
8 |
+
"AutoModel": "modeling_character_bert.CharacterBertForPreTraining",
|
9 |
+
"AutoModelForMaskedLM": "modeling_character_bert.CharacterBertForMaskedLM"
|
10 |
+
},
|
11 |
+
"attention_probs_dropout_prob": 0.1,
|
12 |
+
"character_embeddings_dim": 16,
|
13 |
+
"cnn_activation": "relu",
|
14 |
+
"cnn_filters": [
|
15 |
+
[
|
16 |
+
1,
|
17 |
+
32
|
18 |
+
],
|
19 |
+
[
|
20 |
+
2,
|
21 |
+
32
|
22 |
+
],
|
23 |
+
[
|
24 |
+
3,
|
25 |
+
64
|
26 |
+
],
|
27 |
+
[
|
28 |
+
4,
|
29 |
+
128
|
30 |
+
],
|
31 |
+
[
|
32 |
+
5,
|
33 |
+
256
|
34 |
+
],
|
35 |
+
[
|
36 |
+
6,
|
37 |
+
512
|
38 |
+
],
|
39 |
+
[
|
40 |
+
7,
|
41 |
+
1024
|
42 |
+
]
|
43 |
+
],
|
44 |
+
"hidden_act": "gelu",
|
45 |
+
"hidden_dropout_prob": 0.1,
|
46 |
+
"hidden_size": 768,
|
47 |
+
"initializer_range": 0.02,
|
48 |
+
"intermediate_size": 3072,
|
49 |
+
"layer_norm_eps": 1e-12,
|
50 |
+
"max_position_embeddings": 512,
|
51 |
+
"max_word_length": 50,
|
52 |
+
"mlm_vocab_size": 100000,
|
53 |
+
"model_type": "character_bert",
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_hidden_layers": 12,
|
56 |
+
"num_highway_layers": 2,
|
57 |
+
"tie_word_embeddings": false,
|
58 |
+
"transformers_version": "4.7.0.dev0",
|
59 |
+
"type_vocab_size": 2,
|
60 |
+
"use_cache": true
|
61 |
+
}
|
mlm_vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ece0a0396cc31225ee75a56b46ad584dd566206098f218b1f8fc06ae0da55c81
|
3 |
+
size 728491415
|
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 |
+
{"name_or_path": "helboukkouri/character-bert", "tokenizer_class": "CharacterBertTokenizer", "max_word_length": 50, "do_lower_case": true, "do_basic_tokenize": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "auto_map": {"AutoTokenizer": ["tokenization_character_bert.CharacterBertTokenizer", null]}}
|
vocab.txt
ADDED
File without changes
|