Karols commited on
Commit
810900b
1 Parent(s): 87f86cb

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cl-tohoku/bert-base-japanese",
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": "positive",
13
+ "1": "neutral",
14
+ "2": "negative"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "negative": 2,
20
+ "neutral": 1,
21
+ "positive": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "tokenizer_class": "BertJapaneseTokenizer",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.33.1",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 32000
37
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc21412425ff5ba9f2473d5fb16cc4b2ac81e980e7a40553c7b62f38d35a73d
3
+ size 442546993
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 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
10
+ "model_max_length": 512,
11
+ "never_split": null,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "subword_tokenizer_type": "wordpiece",
15
+ "sudachi_kwargs": null,
16
+ "tokenizer_class": "BertJapaneseTokenizer",
17
+ "unk_token": "[UNK]",
18
+ "word_tokenizer_type": "mecab"
19
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff