Commit
•
24d9799
1
Parent(s):
2c0214e
Upload 5 files
Browse files- config.json +25 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +21 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "outputs_unsup_simcse/encoder",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
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 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.30.2",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 32768
|
25 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4a6cf7259ad76792ec09262bc82638214172b40a3788d60317d3bba81238563
|
3 |
+
size 444897069
|
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
|
|