tmanabe commited on
Commit
2567759
1 Parent(s): 5e04282

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +24 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +11 -0
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 128,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 512,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 128,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 2,
16
+ "num_hidden_layers": 2,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.31.0",
21
+ "type_vocab_size": 1,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c5329866aa556d9236d785c77afb2c5dbc1fa98fd3673b9a935009d30793e95
3
+ size 17483759
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "PreTrainedTokenizerFast",
3
+ "bos_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "unk_token": "[UNK]",
6
+ "sep_token": "[SEP]",
7
+ "pad_token": "[PAD]",
8
+ "cls_token": "[CLS]",
9
+ "mask_token": "[MASK]",
10
+ "model_max_length": 128
11
+ }