bluenguyen commited on
Commit
ce983cc
1 Parent(s): c164766

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/led-base-16384",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "LEDForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_window": [
10
+ 1024,
11
+ 1024,
12
+ 1024,
13
+ 1024,
14
+ 1024,
15
+ 1024
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 768,
21
+ "decoder_attention_heads": 12,
22
+ "decoder_ffn_dim": 3072,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 2,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 12,
28
+ "encoder_ffn_dim": 3072,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 2,
32
+ "gradient_checkpointing": false,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "max_decoder_position_embeddings": 1024,
46
+ "max_encoder_position_embeddings": 16384,
47
+ "model_type": "led",
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.25.1",
52
+ "use_cache": true,
53
+ "vocab_size": 64001
54
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3d9c7be69ba62f90ac17f335a757a847e66be8c304b51aa7b114d42b0de248
3
+ size 689926321
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 16384,
9
+ "name_or_path": "vinai/bartpho-word-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "BartTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff