Pavel Soriano commited on
Commit
6249836
1 Parent(s): c738029

first upload

Browse files
Files changed (5) hide show
  1. config.json +22 -0
  2. pytorch_model.bin +3 -0
  3. sentencepiece.bpe.model +0 -0
  4. tokenizer.json +0 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DPRQuestiontEncoder"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "camembert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "type_vocab_size": 1,
21
+ "vocab_size": 32005
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1ae262d689f595cc7d622961e32a1eda6dc4a02d7edee83a385917a4fb611d
3
+ size 442838427
sentencepiece.bpe.model ADDED
Binary file (811 kB). View file
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff