Hugging Face's logo

HJLEE0106
/
BART_small

Safetensors
bart
Model card Files Community
kse commited on
Commit
e57005a
·
1 Parent(s): e65d02b

initial commit

Browse files
Files changed (8) hide show
  1. added_tokens.json +3 -0
  2. config.json +46 -0
  3. generation_config.json +10 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +73 -0
  8. unigram.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<s>": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cosmoquester/bart-ko-small",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "BartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 2,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 512,
12
+ "decoder_attention_heads": 4,
13
+ "decoder_ffn_dim": 2048,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 3,
16
+ "decoder_start_token_id": 2,
17
+ "dropout": 0.1,
18
+ "encoder_attention_heads": 4,
19
+ "encoder_ffn_dim": 2048,
20
+ "encoder_layerdrop": 0.0,
21
+ "encoder_layers": 3,
22
+ "eos_token_id": 3,
23
+ "forced_eos_token_id": 3,
24
+ "gradient_checkpointing": false,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1",
28
+ "2": "LABEL_2"
29
+ },
30
+ "init_std": 0.02,
31
+ "is_encoder_decoder": true,
32
+ "label2id": {
33
+ "LABEL_0": 0,
34
+ "LABEL_1": 1,
35
+ "LABEL_2": 2
36
+ },
37
+ "max_position_embeddings": 2048,
38
+ "model_type": "bart",
39
+ "num_hidden_layers": 3,
40
+ "pad_token_id": 0,
41
+ "scale_embedding": false,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.40.2",
44
+ "use_cache": false,
45
+ "vocab_size": 32000
46
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 3,
6
+ "forced_eos_token_id": 3,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.40.2",
9
+ "use_cache": false
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2766d9c843001ffa1c5de6f9c675cac1a3fe7f79397b1e86c2172c39f0bb186
3
+ size 162361152
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[BOS]",
3
+ "cls_token": "<s>",
4
+ "eos_token": "[EOS]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
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 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[BOS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[EOS]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "14": {
37
+ "content": "[SEP]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "16": {
45
+ "content": "[MASK]",
46
+ "lstrip": true,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32000": {
53
+ "content": "<s>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "bos_token": "[BOS]",
62
+ "clean_up_tokenization_spaces": true,
63
+ "cls_token": "<s>",
64
+ "eos_token": "[EOS]",
65
+ "errors": "replace",
66
+ "mask_token": "[MASK]",
67
+ "model_max_length": 1000000000000000019884624838656,
68
+ "pad_token": "[PAD]",
69
+ "sep_token": "[SEP]",
70
+ "tokenizer_class": "BartTokenizer",
71
+ "trim_offsets": true,
72
+ "unk_token": "[UNK]"
73
+ }
unigram.json ADDED
The diff for this file is too large to render. See raw diff