masato12 commited on
Commit
11e3562
·
verified ·
1 Parent(s): cdd2c5e

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "masato12/bert-base-japanese-v3-jsts-with-tokenizer",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "problem_type": "regression",
27
+ "transformers_version": "4.33.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 32768
31
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f30393a5d22ba5cb6bb03fb388a185b44b2c5268dd56993e9376c0397a5dd8a
3
+ size 445098516
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d35a42d20841c3e258fad236ce938883649ccb7311ac66282c48c5ad117633f5
3
+ size 112441389
quantize_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Reshape",
8
+ "Sub",
9
+ "Pow",
10
+ "Cast",
11
+ "Gemm",
12
+ "Add",
13
+ "Sqrt",
14
+ "Constant",
15
+ "Unsqueeze",
16
+ "Gather",
17
+ "Concat",
18
+ "ReduceMean",
19
+ "Softmax",
20
+ "Transpose",
21
+ "Shape",
22
+ "Erf",
23
+ "Mul",
24
+ "MatMul",
25
+ "Tanh",
26
+ "Div",
27
+ "Slice"
28
+ ],
29
+ "weight_type": "QInt8"
30
+ }
31
+ }
32
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "do_subword_tokenize": true,
6
+ "do_word_tokenize": true,
7
+ "jumanpp_kwargs": null,
8
+ "mask_token": "[MASK]",
9
+ "mecab_kwargs": {
10
+ "mecab_dic": "unidic_lite"
11
+ },
12
+ "model_max_length": 512,
13
+ "never_split": null,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "subword_tokenizer_type": "wordpiece",
17
+ "sudachi_kwargs": null,
18
+ "tokenizer_class": "BertJapaneseTokenizer",
19
+ "unk_token": "[UNK]",
20
+ "word_tokenizer_type": "mecab"
21
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff