sonoisa commited on
Commit
a3370d3
1 Parent(s): f6d7b07

Fix Japanese Sentence-BERT model

Browse files
config.json CHANGED
@@ -19,8 +19,8 @@
19
  "position_embedding_type": "absolute",
20
  "tokenizer_class": "BertJapaneseTokenizer",
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.13.0",
23
  "type_vocab_size": 2,
24
  "use_cache": true,
25
- "vocab_size": 32768
26
  }
 
19
  "position_embedding_type": "absolute",
20
  "tokenizer_class": "BertJapaneseTokenizer",
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.15.0",
23
  "type_vocab_size": 2,
24
  "use_cache": true,
25
+ "vocab_size": 32000
26
  }
config_sentence_transformers.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "__version__": {
3
  "sentence_transformers": "2.1.0",
4
- "transformers": "4.13.0",
5
  "pytorch": "1.10.0+cu111"
6
  }
7
  }
 
1
  {
2
  "__version__": {
3
  "sentence_transformers": "2.1.0",
4
+ "transformers": "4.15.0",
5
  "pytorch": "1.10.0+cu111"
6
  }
7
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd472ccd434aa590d753bb7155aa96ee9b9a0f37b550729dac3514371a19ea12
3
- size 444910001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178e38a98dc4a3c7f2b2b8ea80183667f8dcbfe283b2ccc70c0185d94b53bf18
3
+ size 442550705
sentence_bert_config.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
  "max_seq_length": 80,
3
- "do_lower_case": false
4
  }
 
1
  {
2
  "max_seq_length": 80,
3
+ "do_lower_case": true
4
  }
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "do_lower_case": false, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "wordpiece", "never_split": null, "mecab_kwargs": {"mecab_dic": "unidic_lite"}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/content/model/", "tokenizer_class": "BertJapaneseTokenizer"}
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "do_lower_case": false, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "wordpiece", "never_split": null, "mecab_kwargs": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/content/model/", "tokenizer_class": "BertJapaneseTokenizer"}
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff