nreimers commited on
Commit
4a24972
1 Parent(s): 956cc57
config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "vocab_size": 30522
21
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:597080ab75b867ef3ba15633bdc5c4cd55c3563ee92840e7af826464b970a0f1
3
+ size 265473819
sentence_bert_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "max_seq_length": 128
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "model_max_length": 512, "special_tokens_map_file": "output/training_nli_distilbert-base-uncased-2020-07-22_10-20-15/0_Transformer/special_tokens_map.json", "full_tokenizer_file": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff