update small (add tag)
Browse files- README.md +1 -0
- README_JA.md +1 -0
- tokenizer_config.json +18 -4
README.md
CHANGED
|
@@ -3,6 +3,7 @@ pipeline_tag: sentence-similarity
|
|
| 3 |
language: ja
|
| 4 |
license: cc-by-sa-4.0
|
| 5 |
tags:
|
|
|
|
| 6 |
- sentence-transformers
|
| 7 |
- feature-extraction
|
| 8 |
- sentence-similarity
|
|
|
|
| 3 |
language: ja
|
| 4 |
license: cc-by-sa-4.0
|
| 5 |
tags:
|
| 6 |
+
- transformers
|
| 7 |
- sentence-transformers
|
| 8 |
- feature-extraction
|
| 9 |
- sentence-similarity
|
README_JA.md
CHANGED
|
@@ -3,6 +3,7 @@ pipeline_tag: sentence-similarity
|
|
| 3 |
language: ja
|
| 4 |
license: cc-by-sa-4.0
|
| 5 |
tags:
|
|
|
|
| 6 |
- sentence-transformers
|
| 7 |
- feature-extraction
|
| 8 |
- sentence-similarity
|
|
|
|
| 3 |
language: ja
|
| 4 |
license: cc-by-sa-4.0
|
| 5 |
tags:
|
| 6 |
+
- transformers
|
| 7 |
- sentence-transformers
|
| 8 |
- feature-extraction
|
| 9 |
- sentence-similarity
|
tokenizer_config.json
CHANGED
|
@@ -1,8 +1,22 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"do_lower_case": false,
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
|
|
|
| 5 |
"mecab_kwargs": {
|
| 6 |
-
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
|
|
|
| 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 |
+
"name_or_path": "cl-tohoku/bert-base-japanese-v2",
|
| 13 |
+
"never_split": null,
|
| 14 |
+
"pad_token": "[PAD]",
|
| 15 |
+
"sep_token": "[SEP]",
|
| 16 |
+
"special_tokens_map_file": null,
|
| 17 |
+
"subword_tokenizer_type": "wordpiece",
|
| 18 |
+
"sudachi_kwargs": null,
|
| 19 |
+
"tokenizer_class": "BertJapaneseTokenizer",
|
| 20 |
+
"unk_token": "[UNK]",
|
| 21 |
+
"word_tokenizer_type": "mecab"
|
| 22 |
}
|