Hugging Face's logo

Xenova
/
opus-mt-ko-en

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files Community
Xenova HF staff commited on
Commit
5310291
•
1 Parent(s): fad360e

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. config.json +60 -0
  2. generation_config.json +16 -0
  3. onnx/decoder_model.onnx +3 -0
  4. onnx/decoder_model_merged.onnx +3 -0
  5. onnx/decoder_model_merged_quantized.onnx +3 -0
  6. onnx/decoder_model_quantized.onnx +3 -0
  7. onnx/decoder_with_past_model.onnx +3 -0
  8. onnx/decoder_with_past_model_quantized.onnx +3 -0
  9. onnx/encoder_model.onnx +3 -0
  10. onnx/encoder_model_quantized.onnx +3 -0
  11. quantize_config.json +125 -0
  12. source.spm +0 -0
  13. special_tokens_map.json +5 -0
  14. target.spm +0 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +12 -0
  17. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ko-en",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "swish",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "MarianMTModel"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bad_words_ids": [
12
+ [
13
+ 65000
14
+ ]
15
+ ],
16
+ "bos_token_id": 0,
17
+ "classif_dropout": 0.0,
18
+ "classifier_dropout": 0.0,
19
+ "d_model": 512,
20
+ "decoder_attention_heads": 8,
21
+ "decoder_ffn_dim": 2048,
22
+ "decoder_layerdrop": 0.0,
23
+ "decoder_layers": 6,
24
+ "decoder_start_token_id": 65000,
25
+ "decoder_vocab_size": 65001,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 8,
28
+ "encoder_ffn_dim": 2048,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 0,
32
+ "extra_pos_embeddings": 65001,
33
+ "forced_eos_token_id": 0,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 512,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "marian",
49
+ "normalize_before": false,
50
+ "normalize_embedding": false,
51
+ "num_beams": 6,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 65000,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "transformers_version": "4.32.0.dev0",
58
+ "use_cache": true,
59
+ "vocab_size": 65001
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 65000
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 65000,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 6,
14
+ "pad_token_id": 65000,
15
+ "transformers_version": "4.32.0.dev0"
16
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6005cf82395d5981f33b856afe794f13ab0f31a3c696d4c0cf70ae2db869c31
3
+ size 368725660
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f522bb11361e56d5c77b156b794a5e2c123f1a5a1eb69e0db8e1d21d399f246
3
+ size 368961142
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8133e924cac321c334ca99b69b34d5bc08ffebe929b24244545d57330b32b0f3
3
+ size 93819732
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338df537cff1d7a8546c5a99374cf6485c63740831d770448fc3ec6294806ae5
3
+ size 93448376
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b52aa52401399c0a40f2bb665a6b8ce83c62c096f838042d5c6661dbb33d585
3
+ size 356075151
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a75b0b2aaa19d87f5856f6b2b26001e3c8f0a14317cf376438687f29b9be2d
3
+ size 90176912
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0b3965f9030e4d479d6d9f113cfdc2e61b074240cbc80c47895d94e684dd7c
3
+ size 209938220
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210e1d2cb5b457cdeeffe288099cc9d1df9f13c35dc3d39fde4ba252af877380
3
+ size 52899741
quantize_config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "encoder_model": {
6
+ "op_types": [
7
+ "ReduceMean",
8
+ "Expand",
9
+ "Unsqueeze",
10
+ "Softmax",
11
+ "Where",
12
+ "Pow",
13
+ "Equal",
14
+ "ConstantOfShape",
15
+ "Shape",
16
+ "Div",
17
+ "Reshape",
18
+ "Sub",
19
+ "Cast",
20
+ "Concat",
21
+ "Constant",
22
+ "Mul",
23
+ "Sigmoid",
24
+ "Gather",
25
+ "Sqrt",
26
+ "Transpose",
27
+ "MatMul",
28
+ "Range",
29
+ "Add"
30
+ ],
31
+ "weight_type": "QInt8"
32
+ },
33
+ "decoder_with_past_model": {
34
+ "op_types": [
35
+ "ReduceMean",
36
+ "Expand",
37
+ "Unsqueeze",
38
+ "Softmax",
39
+ "Where",
40
+ "Pow",
41
+ "Equal",
42
+ "ConstantOfShape",
43
+ "Shape",
44
+ "Div",
45
+ "Reshape",
46
+ "Sub",
47
+ "Cast",
48
+ "Concat",
49
+ "Constant",
50
+ "Mul",
51
+ "Sigmoid",
52
+ "Gather",
53
+ "Sqrt",
54
+ "Transpose",
55
+ "MatMul",
56
+ "Range",
57
+ "Add"
58
+ ],
59
+ "weight_type": "QInt8"
60
+ },
61
+ "decoder_model": {
62
+ "op_types": [
63
+ "ReduceMean",
64
+ "Expand",
65
+ "Squeeze",
66
+ "Unsqueeze",
67
+ "Softmax",
68
+ "Where",
69
+ "Less",
70
+ "Pow",
71
+ "Equal",
72
+ "ConstantOfShape",
73
+ "Shape",
74
+ "Div",
75
+ "Reshape",
76
+ "Sub",
77
+ "Cast",
78
+ "Concat",
79
+ "Constant",
80
+ "Mul",
81
+ "Sigmoid",
82
+ "Gather",
83
+ "Sqrt",
84
+ "Slice",
85
+ "Transpose",
86
+ "MatMul",
87
+ "Range",
88
+ "Add"
89
+ ],
90
+ "weight_type": "QInt8"
91
+ },
92
+ "decoder_model_merged": {
93
+ "op_types": [
94
+ "ReduceMean",
95
+ "Expand",
96
+ "Squeeze",
97
+ "Unsqueeze",
98
+ "Softmax",
99
+ "If",
100
+ "Less",
101
+ "Where",
102
+ "Equal",
103
+ "Pow",
104
+ "ConstantOfShape",
105
+ "Shape",
106
+ "Div",
107
+ "Reshape",
108
+ "Sub",
109
+ "Cast",
110
+ "Concat",
111
+ "Constant",
112
+ "Mul",
113
+ "Sigmoid",
114
+ "Gather",
115
+ "Sqrt",
116
+ "Slice",
117
+ "Transpose",
118
+ "MatMul",
119
+ "Range",
120
+ "Add"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
source.spm ADDED
Binary file (842 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
Binary file (813 kB). View file
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "</s>",
4
+ "model_max_length": 512,
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": "kor",
8
+ "sp_model_kwargs": {},
9
+ "target_lang": "eng",
10
+ "tokenizer_class": "MarianTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff