osiria commited on
Commit
4c2bfab
1 Parent(s): d062fb3

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +23 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +1 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertModel"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "initializer_range": 0.02,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "distilbert",
13
+ "n_heads": 12,
14
+ "n_layers": 6,
15
+ "pad_token_id": 0,
16
+ "qa_dropout": 0.1,
17
+ "seq_classif_dropout": 0.2,
18
+ "sinusoidal_pos_embds": false,
19
+ "tie_weights_": true,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.30.0.dev0",
22
+ "vocab_size": 30785
23
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1cbd83a697be06f2a42c7deb167ee15e7aa798616796f59b605d6feff910589
3
+ size 266290041
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "do_basic_tokenize": true, "never_split": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff