hyunwoongko commited on
Commit
dc25414
1 Parent(s): 3b0774c

initial commit

Browse files
Files changed (4) hide show
  1. config.json +49 -0
  2. pytorch_model.bin +3 -0
  3. sentencepiece.bpe.model +0 -0
  4. tokenizer.json +0 -0
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 12,
18
+ "dropout": 0.1,
19
+ "encoder_attention_heads": 16,
20
+ "encoder_ffn_dim": 4096,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 12,
23
+ "eos_token_id": 2,
24
+ "id2label": {
25
+ "0": "LABEL_0",
26
+ "1": "LABEL_1",
27
+ "2": "LABEL_2"
28
+ },
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1,
34
+ "LABEL_2": 2
35
+ },
36
+ "max_position_embeddings": 1024,
37
+ "model_type": "mbart",
38
+ "normalize_before": true,
39
+ "normalize_embedding": true,
40
+ "task_specific_params": {},
41
+ "num_beams": 5,
42
+ "max_length": 1024,
43
+ "num_hidden_layers": 12,
44
+ "output_past": true,
45
+ "pad_token_id": 1,
46
+ "scale_embedding": true,
47
+ "static_position_embeddings": false,
48
+ "vocab_size": 57526
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd580ab172452444e97b9a0d8c31b262f624415eb1f35aa69c13a36e3de2986
3
+ size 1655262259
sentencepiece.bpe.model ADDED
Binary file (1.3 MB). View file
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff