mr4 commited on
Commit
85e604d
1 Parent(s): fa12432

Add first version

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mr4/bert-base-jp-sentiment-analysis",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "negative",
15
+ "1": "positive"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "negative": 0,
21
+ "positive": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_length": 256,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "padding": "max_length",
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "tokenizer_class": "BertJapaneseTokenizer",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.27.1",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 32768
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5837097dd474ddfd4718193c1d9c3df1ad5b7ab33cf0ec92ab033195fe39f18b
3
+ size 444904821
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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "do_subword_tokenize": true,
5
+ "do_word_tokenize": true,
6
+ "jumanpp_kwargs": null,
7
+ "mask_token": "[MASK]",
8
+ "mecab_kwargs": {
9
+ "mecab_dic": "unidic_lite"
10
+ },
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "never_split": null,
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "special_tokens_map_file": null,
16
+ "subword_tokenizer_type": "wordpiece",
17
+ "sudachi_kwargs": null,
18
+ "tokenizer_class": "BertJapaneseTokenizer",
19
+ "tokenizer_file": null,
20
+ "unk_token": "[UNK]",
21
+ "word_tokenizer_type": "mecab"
22
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff